Pooling in convolutional neural networks for medical image analysis: a survey and an empirical study
Open accessThe DOI matches its Crossref record; 123 of the 123 references it cites were found in a registry or an index.
Abstract
Convolutional neural networks (CNN) are widely used in computer vision and medical image analysis as the state-of-the-art technique. In CNN, pooling layers are included mainly for downsampling the feature maps by aggregating features from local regions. Pooling can help CNN to learn invariant features and reduce computational complexity. Although the max and the average pooling are the widely used ones, various other pooling techniques are also proposed for different purposes, which include techniques to reduce overfitting, to capture higher-order information such as correlation between features, to capture spatial or structural information, etc. As not all of these pooling techniques are well-explored for medical image analysis, this paper provides a comprehensive review of various pooling techniques proposed in the literature of computer vision and medical image analysis. In addition, an extensive set of experiments are conducted to compare a selected set of pooling techniques on two different medical image classification problems, namely HEp-2 cells and diabetic retinopathy image classification. Experiments suggest that the most appropriate pooling mechanism for a particular classification task is related to the scale of the class-specific features with respect to the image size. As this is the first work focusing on pooling techniques for the application of medical image analysis, we believe that this review and the comparative study will provide a guideline to the choice of pooling mechanisms for various medical image analysis tasks. In addition, by carefully choosing the pooling operations with the standard ResNet architecture, we show new state-of-the-art results on both HEp-2 cells and diabetic retinopathy image datasets.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
1 retracted
Wang, S., Zhang⋆, Y., Cheng, X., Zhang, X., & Zhang, Y. (2021) · Computational and Mathematical Methods in Medicine · doi:10.1155/2021/6633755 · Cited by 78
RetractedDeep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 4×
“The average pooling and the max pooling [6] are widely used in CNNs [46, 49, 51, 59] because of their simplicity— they do not have any parameters to tune.”
BackgroundMethodInfluentialDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
CBAM: Convolutional Block Attention Module
Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_1 · Cited by 25,853
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2016) · arXiv · doi:10.48550/arxiv.1606.00915 · Cited by 22,392
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392 · cited 2×
“Atrous Spatial Pyramid Pooling (ASPP) [12] Segmentation [12] Multi-scale retinal vessel segmentation [134] Retina”
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599 · cited 1×
“, PASCAL VOC 2012 [29], Cityscapes [23], CIFAR10 [58]) and their applicability for medical image classification has not been well-investigated.”
BackgroundThe Cityscapes Dataset for Semantic Urban Scene Understanding
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.350 · Cited by 12,433 · cited 2×
“For example, soft pooling (e.g., [42, 55, 90, 124, 129]) is proposed to take advantages of both the widely used max and average pooling; stochastic pooling (e.g., [39, 101, 132, 142, 143]) is proposed to overcome the overfitting issue in CNN training; spatial pyramid pooling and its variants are to capture spatial or s…”
BackgroundSpatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2389824 · Cited by 11,971
Convolutional neural networks: an overview and application in radiology
Yamashita, R., Nishio, M., Do, R. K. G., & Togashi, K. (2018) · Insights into Imaging · doi:10.1007/s13244-018-0639-9 · Cited by 4,682 · cited 1×
“In medical image analysis, pooling can help to handle variance in lesion sizes [3] and positions [94].”
BackgroundWang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., & Summers, R. M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.369 · Cited by 4,616 · cited 6×
“Various such approximations are used, including Log-Sum-Exp pooling (LSE) [55, 90, 124], Polynomial pooling [129], Learned-Norm pooling [42], ‘ p pooling [7], a Integration ( a I ) pooling [28], Rank-based pooling [99, 101], Dynamic pooling [84], Smooth-Maximum pooling [5], Soft pooling [107], Maxfun pooling [26], Ord…”
BackgroundMethodInfluentialStriving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447
Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
Tajbakhsh, N., Shin, J. Y., Gurudu, S. R., Hurst, R. T., Kendall, C. B., Gotway, M. B., & Liang, J. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2535302 · Cited by 3,277 · cited 2×
“For this dataset, the weights of the CNN were initialized with the weights of an ImageNet pre-trained model as recommended in [109].”
MethodLinear spatial pyramid matching using sparse coding for image classification
Yang, J., Yu, K., Gong, Y., & Huang, T. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206757 · Cited by 2,828 · cited 3×
“The Root-Mean-Square pooling [53] is a special case (r 1⁄4 2) of GM.”
BackgroundAggregating local descriptors into a compact image representation
Jegou, H., Douze, M., Schmid, C., & Perez, P. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5540039 · Cited by 2,692 · cited 5×
“A recent work [80] reports signifi-cant performance improvement by the learned aggregation schemes (BoW, VLAD and FV) over average pooling for video classification.”
BackgroundInfluentialNetVLAD: CNN Architecture for Weakly Supervised Place Recognition
Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., & Sivic, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.572 · Cited by 2,584 · cited 5×
“A recent work [80] reports signifi-cant performance improvement by the learned aggregation schemes (BoW, VLAD and FV) over average pooling for video classification.”
MethodInfluentialBilinear CNN Models for Fine-Grained Visual Recognition
Lin, T.-Y., RoyChowdhury, A., & Maji, S. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.170 · Cited by 2,135
NetVLAD: CNN architecture for weakly supervised place recognitionPreprint
Arandjelović, R., Gronát, P., Torii, A., Pajdla, T., & Šivic, J. (2015) · arXiv (Cornell University) · Cited by 1,790
Fisher Kernels on Visual Vocabularies for Image Categorization
Perronnin, F., & Dance, C. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383266 · Cited by 1,641 · cited 2×
“Note that in addition to CNNs, max and average pooling also have been well-explored in traditional feature encoding approaches such as, bag-of-words [24] and its variations such as sparse coding [53], vector of locally aggregated descriptors [52] and Fisher vectors [88] (discussed in Sect.”
BackgroundEvaluation of Pooling Operations in Convolutional Architectures for Object Recognition
Scherer, D., Müller, A., & Behnke, S. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15825-4_10 · Cited by 1,503 · cited 1×
“Convolutional neural networks (CNNs) are the state-of-the-art methods for various computer vision and medical image analysis tasks such as image classification [55, 95, 98, 109, 124, 126] and segmentation [35, 109, 118].”
MethodMulti-scale Orderless Pooling of Deep Convolutional Activation Features
Gong, Y., Wang, L., Guo, R., & Lazebnik, S. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10584-0_26 · Cited by 1,030 · cited 1×
“Methods also proposed to integrate these approaches with CNN as feature aggregation techniques by either using them with features extracted from pre-trained CNN [21, 37, 138], or learning CNNs together with the parameters of BoW [80, 87], VLAD [2, 80, 140] and FV [80] in an end-to-end manner.”
MethodGao, Y., Beijbom, O., Zhang, N., & Darrell, T. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.41 · Cited by 871 · cited 4×
“…pooling and its variants are to capture spatial or structural information in the images (e.g., [45, 91, 130]); higher-order pooling (e.g., [25, 31, 34, 69–71, However, most of these approaches were proposed for and evaluated on computer vision image datasets (e.g., PASCAL VOC 2012 [29],…”
BackgroundMethodInfluentialParticular object retrieval with integral max-pooling of CNN activations
Tolias, G., Sicre, R., & Jégou, H. (2015) · arXiv · doi:10.48550/arxiv.1511.05879 · Cited by 744
Multiple instance learning: A survey of problem characteristics and applications
Carbonneau, M.-A., Cheplygina, V., Granger, E., & Gagnon, G. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.10.009 · Cited by 740 · cited 1×
“…are differential approximation of max pooling, they are widely explored in (non-CNN based) Multiple Instance Learning approaches in computer vision [8] and medical image analysis [76, 135] (Table 2), in addition to CNN-based image classification [28, 42, 124, 144] and segmentation [90, 129].”
MethodFrom image-level to pixel-level labeling with Convolutional Networks
Pinheiro, P. O., & Collobert, R. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298780 · Cited by 673 · cited 8×
“Rank-based stochastic pooling [101] Classification [101] Abnormal breast identification [148] Breast Mixed pooling [139] Classification [139] Brain tumor segmentation [10] MRI (brain) Hybrid pooling [112] Classification Fractional max pooling [39] Classification [39] Retinopathy image classification [40] Retina Sparsity-bas…”
BackgroundMethodInfluentialDeep filter banks for texture recognition and segmentation
Cimpoi, M., Maji, S., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299007 · Cited by 646 · cited 1×
“using them with features extracted from pre-trained CNN [21, 37, 138], or learning CNNs together with the parameters of BoW [80, 87], VLAD [2, 80, 140] and FV [80] in an end-to-end manner.”
MethodYang, F., Choi, W., & Lin, Y. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.234 · Cited by 608 · cited 1×
“Various approaches [30, 43, 45, 91, 92, 115, 117, 130, 136, 145] have been proposed to encode local structure information in the pooled representation.”
BackgroundGlobal Second-Order Pooling Convolutional Networks
Gao, Z., Xie, J., Wang, Q., & Li, P. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00314 · Cited by 524 · cited 5×
“This idea is then extended with CNN features in [25, 34, 69–71 , 141 ].”
BackgroundMethodInfluentialDeep image mining for diabetic retinopathy screening
Quellec, G., Charrière, K., Boudi, Y., Cochener, B., & Lamard, M. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.04.012 · Cited by 520 · cited 1×
“Most of the existing work [1, 40, 56, 93] for DR image analysis focus on building custom CNN architectures.”
BackgroundSemantic Segmentation with Second-Order Pooling
Carreira, J., Caseiro, R., Batista, J., & Sminchisescu, C. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33786-4_32 · Cited by 458 · cited 3×
“The max and the average second-order pooling are defined in [9] as follows: where u i 2 R d is the i th feature descriptor (e.g., SIFT [72]) from region R , d is the dimensionality of u i and u i (cid:2) u Ti is the outer product between descriptor s i with itself, capturing the pairwise…”
BackgroundMethodZhang, R., Zhu, F., Liu, J., & Liu, G. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2936913 · Cited by 420 · cited 1×
“Spatial pyramid pooling [45] Classification, Detection [45] Hand gesture recognition [110], Image steganalysis [146] Brain image segmentation [118] Prostate image segmentation [35] Tumor segmentation for rectal cancer radiotherapy [79] MRI (brain) MRI (prostate) MRI, CT (rectum)”
MethodMixed Pooling for Convolutional Neural Networks
Yu, D., Wang, H., Chen, P., & Wei, Z. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-11740-9_34 · Cited by 409 · cited 4×
“Mixed-pooling [139], Hybrid pooling [112], Stochastic pooling [142], Rank-Based Stochastic pooling [101], Max pooling dropout [132], Stochastic Spatial Sampling (S3 pooling) [143] and Fractional Max pooling [39] are proposed to reduce overfitting by introducing various forms of randomness in pooling configurations and…”
BackgroundInfluentialCABNet: Category Attention Block for Imbalanced Diabetic Retinopathy Grading
He, A., Li, T., Li, N., Wang, K., & Fu, H. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3023463 · Cited by 395 · cited 1×
“Convolutional Block Attention Module (CBAM) [131] Classification [131] Diabetic retinopathy grading [44] Retina”
BackgroundSpatial Pyramid-Enhanced NetVLAD With Weighted Triplet Loss for Place Recognition
Yu, J., Zhu, C., Zhang, J., Huang, Q., & Tao, D. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2908982 · Cited by 352 · cited 5×
“A recent work [80] reports signifi-cant performance improvement by the learned aggregation schemes (BoW, VLAD and FV) over average pooling for video classification.”
MethodInfluentialKernel Pooling for Convolutional Neural Networks
Cui, Y., Zhou, F., Wang, J., Liu, X., Lin, Y., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.325 · Cited by 339 · cited 5×
“This idea is then extended with CNN features in [25, 34, 69–71 , 141 ].”
BackgroundMethodInfluentialGraham, B. (2014) · arXiv · doi:10.48550/arxiv.1412.6071 · Cited by 337 · cited 6×
“In S3 pooling [143] and Fractional Max Pooling [39] randomness is applied at the spatial sampling stage of the pooling.”
BackgroundMethodInfluentialDeep Filter Banks for Texture Recognition, Description, and Segmentation
Cimpoi, M., Maji, S., Kokkinos, I., & Vedaldi, A. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-015-0872-3 · Cited by 335
Bilinear Convolutional Neural Networks for Fine-Grained Visual Recognition
Lin, T.-Y., RoyChowdhury, A., & Maji, S. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2723400 · Cited by 328
Li, P., Xie, J., Wang, Q., & Gao, Z. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00105 · Cited by 310
A Large-Scale Database and a CNN Model for Attention-Based Glaucoma Detection
Li, L., Xu, M., Liu, H., Li, Y., Wang, X., Jiang, L., Wang, Z., Fan, X., & Wang, N. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2927226 · Cited by 303 · cited 4×
“In [67], a separate subnetwork is used to learn the”
BackgroundMethodInfluentialSpatial pyramid co-occurrence for image classification
Yang, Y., & Newsam, S. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126403 · Cited by 301 · cited 1×
“This interaction may capture additional details such as object co-occurrence [137].”
BackgroundIs Second-Order Information Helpful for Large-Scale Visual Recognition?
Li, P., Xie, J., Wang, Q., & Zuo, W. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.228 · Cited by 294 · cited 4×
“…and its variants are to capture spatial or structural information in the images (e.g., [45, 91, 130]); higher-order pooling (e.g., [25, 31, 34, 69–71, However, most of these approaches were proposed for and evaluated on computer vision image datasets (e.g., PASCAL VOC 2012 [29], Cityscapes…”
BackgroundMethodInfluentialRetrieval of Brain Tumors by Adaptive Spatial Pooling and Fisher Vector Representation
Cheng, J., Yang, W., Huang, M., Huang, W., Jiang, J., Zhou, Y., Yang, R., Zhao, J., Feng, Y., Feng, Q., et al. (2016) · PLOS ONE · doi:10.1371/journal.pone.0157112 · Cited by 293
Zoom-in-Net: Deep Mining Lesions for Diabetic Retinopathy Detection
Wang, Z., Yin, Y., Shi, J., Fang, W., Li, H., & Wang, X. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-66179-7_31 · Cited by 281 · cited 3×
“Note that compared to Zoom-in-net [127], our method is not only simple, but also make use of a standard network architecture (ResNet-18) with different pooling mechanisms.”
BackgroundMethodLearning Pooling for Convolutional Neural Network
Sun, M., Song, Z., Jiang, X., Pan, J., & Pang, Y. (2017) · Neurocomputing · doi:10.1016/j.neucom.2016.10.049 · Cited by 274 · cited 1×
“In Learning pooling (LEAP) [108] strided convolutions are applied independently from each channel of the feature maps to reduce the number of parameters required with strided convolutions.”
MethodRefining activation downsampling with SoftPool
Stergiou, A., Poppe, R., & Kalliatakis, G. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01019 · Cited by 271 · cited 2×
“SoftPool [107] Classification, Action recognition [107] – –”
MethodTI-POOLING: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks
Laptev, D., Savinov, N., Buhmann, J. M., & Pollefeys, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.38 · Cited by 255 · cited 5×
“…image analysis for different problems, including HEp-2 cell image Other approaches Transformation Invariant Pooling (TI-Pooling) [61] Classification [61] Neuronal structures segmentation [61] Microscopy Hierarchical mix pooling [78] - HEp-2 cell image classification [78] X-Ray image classification…”
BackgroundMethodInfluentialMurray, N., & Perronnin, F. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.317 · Cited by 238 · cited 6×
“However, different channels of the same set of feature maps are highly correlated and should be treated jointly [83].”
BackgroundMethodInfluentialFC^4: Fully Convolutional Color Constancy with Confidence-Weighted Pooling
Hu, Y., Wang, B., & Lin, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.43 · Cited by 233 · cited 1×
“Attention-based pooling [36, 41, 50, 67, 73, 89, 127] has received much focus recently.”
BackgroundImproved Bilinear Pooling with CNNs
Lin, T.-Y., & Maji, S. (2017) · Procedings of the British Machine Vision Conference 2017 · doi:10.5244/c.31.117 · Cited by 224
HEp-2 Cell Image Classification With Deep Convolutional Neural Networks
Gao, Z., Wang, L., Zhou, L., & Zhang, J. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2016.2526603 · Cited by 219 · cited 1×
“Recently, CNN [33, 65]-based approaches also became popular for HEp-2 cell image classification.”
BackgroundAccurate classification of cherry fruit using deep CNN based on hybrid pooling approach
Momeny, M., Jahanbakhshi, A., Jafarnezhad, K., & Zhang, Y.-D. (2020) · Postharvest Biology and Technology · doi:10.1016/j.postharvbio.2020.111204 · Cited by 183 · cited 1×
“Hybrid pooling [112] Classification [82, 112, 113] – –”
Max-Pooling Dropout for Regularization of Convolutional Neural Networks
Wu, H., & Gu, X. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-26532-2_6 · Cited by 181 · cited 3×
“In this experiment, we investigate different stochastic pooling approaches to reduce overfitting, such as stochastic pooling [142], max pooling dropout [132], and S3 pooling [143].”
BackgroundMethodInfluentialBag-of-Words Representation in Image Annotation: A Review
Tsai, C.-F. (2012) · ISRN Artificial Intelligence · doi:10.5402/2012/376804 · Cited by 180 · cited 1×
“…Descriptors (VLAD) [52] and Fisher Vectors (FV) [88] are well-known (non-CNN-based) feature encoding and aggregation techniques for order-less representation of handcrafted local descriptors, and have been widely used in Computer Vision [24, 52, 81, 88] and Medical Imaging [77, 114] community.”
Alcoholism Detection by Data Augmentation and Convolutional Neural Network with Stochastic Pooling
Wang, S.-H., Lv, Y.-D., Sui, Y., Liu, S., Wang, S.-J., & Zhang, Y.-D. (2018) · Journal of Medical Systems · doi:10.1007/s10916-017-0845-x · Cited by 176
Detail-Preserving Pooling in Deep Networks
Saeedan, F., Weber, N., Goesele, M., & Roth, S. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00949 · Cited by 173
Bags of Local Convolutional Features for Scalable Instance Search
Mohedano, E., McGuinness, K., O'Connor, N. E., Salvador, A., Marqués, F., & Giró-i-Nieto, X. (2016) · International Conference on Multimedia Retrieval · doi:10.1145/2911996.2912061 · Cited by 169 · cited 1×
“…Descriptors (VLAD) [52] and Fisher Vectors (FV) [88] are well-known (non-CNN-based) feature encoding and aggregation techniques for order-less representation of handcrafted local descriptors, and have been widely used in Computer Vision [24, 52, 81, 88] and Medical Imaging [77, 114] community.”
Christlein, V., Spranger, L., Seuret, M., Nicolaou, A., Král, P., & Maier, A. (2019) · IAPR International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2019.00177 · Cited by 167 · cited 3×
“…Similarity Learning [74] – – Higher-order pooling [19] Action recognition [19] – – Detachable second-order pooling [66] Classification [66] – – [20] Witter identification and document classification [20] – – Adaptive spatial pooling [75] Classification [75] Retrieving brain tumors [ Notations:…”
BackgroundLearned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks
Gulcehre, C., Cho, K., Pascanu, R., & Bengio, Y. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-662-44848-9_34 · Cited by 167 · cited 6×
“Learned-norm pooling [42] Classification [42] – –”
BackgroundMethodInfluentialZhang, Y.-D., Pan, C., Chen, X., & Wang, F. (2018) · Journal of Computational Science · doi:10.1016/j.jocs.2018.05.005 · Cited by 163
LIP: Local Importance-Based Pooling
Gao, Z., Wang, L., & Wu, G. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00345 · Cited by 161
Wang, S.-H., Tang, C., Sun, J., Yang, J., Huang, C., Phillips, P., & Zhang, Y.-D. (2018) · Frontiers in Neuroscience · doi:10.3389/fnins.2018.00818 · Cited by 158 · cited 3×
“Stochastic pooling [142] Classification [142] Multiple sclerosis identification [122] MRI (brain)”
BackgroundGeometric ℓp-norm feature pooling for image classification
Feng, J., Ni, B., Tian, Q., & Yan, S. (2011) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2011.5995370 · Cited by 154 · cited 3×
“On the other hand, Geometric ‘p-Norm pooling [30] aims to capture local structure information (e.”
BackgroundLearning to detect chest radiographs containing pulmonary lesions using visual attention networks
Pesce, E., Joseph Withey, S., Ypsilantis, P.-P., Bakewell, R., Goh, V., & Montana, G. (2019) · Medical Image Analysis · doi:10.1016/j.media.2018.12.007 · Cited by 126 · cited 2×
“Attention-based pooling [36, 41, 50, 67, 73, 89, 127] has received much focus recently.”
BackgroundNew Deep Neural Nets for Fine-Grained Diabetic Retinopathy Recognition on Hybrid Color Space
Vo, H. H., & Verma, A. (2016) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2016.0049 · Cited by 124 · cited 1×
“For example, multiple filter sizes and different color spaces were explored for fine-grained classification of DR lesions in [116].”
BackgroundSecond-Order Pooling for Graph Neural Networks
Wang, Z., & Ji, S. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2999032 · Cited by 123 · cited 1×
“Graph pooling [125] Graph classification [125] – –”
BackgroundPose pooling kernels for sub-category recognition
Zhang, N., Farrell, R., & Darrell, T. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248364 · Cited by 121 · cited 3×
“To overcome this, in [145] a part-based pooling strategy is proposed for finegrained image classification.”
BackgroundMethodRunPool: A Dynamic Pooling Layer for Convolution Neural Network
Jie, H. J., & Wanda, P. (2020) · International Journal of Computational Intelligence Systems · doi:10.2991/ijcis.d.200120.002 · Cited by 112
A mix-pooling CNN architecture with FCRF for brain tumor segmentation
Chang, J., Zhang, L., Gu, N., Zhang, X., Ye, M., Yin, R., & Meng, Q. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.11.047 · Cited by 107 · cited 2×
“…pooling [101] Classification [101] Abnormal breast identification [148] Breast Mixed pooling [139] Classification [139] Brain tumor segmentation [10] MRI (brain) Hybrid pooling [112] Classification Fractional max pooling [39] Classification [39] Retinopathy image classification [40] Retina…”
BackgroundMethodCross-Convolutional-Layer Pooling for Image Recognition
Liu, L., Shen, C., & van den Hengel, A. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2637921 · Cited by 104 · cited 2×
“For example, in Cross Convolutional Layer pooling [73], the feature vectors from the feature map of a particular layer are weighted by each of feature maps from its subsequent layer.”
BackgroundS3Pool: Pooling with Stochastic Spatial Sampling
Zhai, S., Wu, H., Kumar, A., Cheng, Y., Lu, Y., Zhang, Z. M., & Feris, R. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.426 · Cited by 99 · cited 7×
“In S3 pooling [143] and Fractional Max Pooling [39] randomness is applied at the spatial sampling stage of the pooling.”
BackgroundMethodInfluentialRank-based pooling for deep convolutional neural networks
Shi, Z., Ye, Y., & Wu, Y. (2016) · Neural Networks · doi:10.1016/j.neunet.2016.07.003 · Cited by 97
Convolutional neural network with spatial pyramid pooling for hand gesture recognition
Tan, Y. S., Lim, K. M., Connie, T., Lee, C. P., & Low, C.-Y. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05337-0 · Cited by 96
Wang, S., Jiang, Y., Hou, X., Cheng, H., & Du, S. (2017) · IEEE Access · doi:10.1109/access.2017.2736558 · Cited by 96 · cited 1×
“Rank-based pooling [101] Classification [101] Cerebral micro-bleed detection [120] MRI (brain)”
MethodMulti-scale pyramid pooling for deep convolutional representation
Yoo, D., Park, S., Lee, J.-Y., & Kweon, I. S. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2015.7301274 · Cited by 95 · cited 1×
“Methods also proposed to integrate these approaches with CNN as feature aggregation techniques by either using them with features extracted from pre-trained CNN [21, 37, 138], or learning CNNs together with the parameters of BoW [80, 87], VLAD [2, 80, 140] and FV [80] in an end-to-end manner.”
MethodXu, Y., Zhu, J.-Y., Chang, E., & Tu, Z. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247772 · Cited by 90 · cited 6×
“Histopathology cancer image classification [135] Histopathology”
BackgroundMethodInfluentialManivannan, S., Li, W., Akbar, S., Wang, R., Zhang, J., & McKenna, S. J. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.09.015 · Cited by 87 · cited 11×
“As the training set of Task 1 dataset contains a smaller number (13, 596) of images and its test set is inaccessible, we used the Task 2 dataset to extract 26, 078 cell images as explained in [77].”
BackgroundMethodInfluentialSelf-citationHEp-2 Cell Classification Using Shape Index Histograms With Donut-Shaped Spatial Pooling
Larsen, A., Vestergaard, J. S., & Larsen, R. (2014) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2014.2318434 · Cited by 86 · cited 3×
“Donut-shaped spatial pooling [62] – Cell image classification [62] HEp-2 cells”
BackgroundLearning Bag-of-Features Pooling for Deep Convolutional Neural Networks
Passalis, N., & Tefas, A. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.614 · Cited by 84 · cited 5×
“A recent work [80] reports signifi-cant performance improvement by the learned aggregation schemes (BoW, VLAD and FV) over average pooling for video classification.”
MethodInfluentialFeature-transfer network and local background suppression for microaneurysm detection
Zhang, X., Wu, J., Meng, M., Sun, Y., & Sun, W. (2020) · Machine Vision and Applications · doi:10.1007/s00138-020-01119-9 · Cited by 80
Chen, Y., Ma, G., Yuan, C., Li, B., Zhang, H., Wang, F., & Hu, W. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107321 · Cited by 68 · cited 1×
“Structure based graph pooling [14] Action recognition [14] – –”
BackgroundWiliem, A., Sanderson, C., Wong, Y., Hobson, P., Minchin, R. F., & Lovell, B. C. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2013.10.014 · Cited by 65 · cited 10×
“Both in [130] and [77] CPM was used with traditional feature representations such as bag-of-words and not with CNNs. Note that CPM requires additional input in the form of segmentation masks to identify the border of each cell.”
BackgroundMethodInfluentialMen, K., Boimel, P. J., Janopaul-Naylor, J. R., Zhong, H., Huang, M., Geng, H., Cheng, C., Fan, Y., Plastaras, J. P., Ben‐Josef, E., et al. (2018) · Physics in Medicine and Biology · doi:10.1088/1361-6560/aada6c · Cited by 65
AlphaMEX: A smarter global pooling method for convolutional neural networks
Zhang, B., Zhao, Q., Feng, W., & Lyu, S. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.07.079 · Cited by 64 · cited 1×
“…are differential approximation of max pooling, they are widely explored in (non-CNN based) Multiple Instance Learning approaches in computer vision [8] and medical image analysis [76, 135] (Table 2), in addition to CNN-based image classification [28, 42, 124, 144] and segmentation [90, 129].”
MethodHybrid pooling for enhancement of generalization ability in deep convolutional neural networks
Tong, Z., & Tanaka, G. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.12.036 · Cited by 58 · cited 1×
“Hybrid pooling [112] Classification [82, 112, 113] – –”
A dynamic pooling based convolutional neural network approach to detect chronic kidney disease
Bhaskar, N., & Suchetha, M. (2020) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2020.102068 · Cited by 55 · cited 1×
“…including Log-Sum-Exp pooling (LSE) [55, 90, 124], Polynomial pooling [129], Learned-Norm pooling [42], ‘ p pooling [7], a Integration ( a I ) pooling [28], Rank-based pooling [99, 101], Dynamic pooling [84], Smooth-Maximum pooling [5], Soft pooling [107], Maxfun pooling [26], Ordinal pooling [60].”
MethodPrecise proximal femur fracture classification for interactive training and surgical planning
Jiménez-Sánchez, A., Kazi, A., Albarqouni, S., Kirchhoff, C., Biberthaler, P., Navab, N., Kirchhoff, S., & Mateus, D. (2020) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-020-02150-x · Cited by 55
Adaptive spatial pooling for image classification
Liu, Y., Zhang, Y., Zhang, X.-Y., & Liu, C. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.01.030 · Cited by 53 · cited 1×
“Adaptive spatial pooling [75] Classification [75] Retrieving brain tumors [17] CE-MRI (brain)”
BackgroundStatistically-Motivated Second-Order Pooling
Yu, K., & Salzmann, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01234-2_37 · Cited by 53
Concentric Circle Pooling in Deep Convolutional Networks for Remote Sensing Scene Classification
Qi, K., Guan, Q., Yang, C., Peng, F., Shen, S., & Wu, H. (2018) · Remote Sensing · doi:10.3390/rs10060934 · Cited by 52 · cited 3×
“Concentric circle pooling [91] Remote sensing scene classification [91] – –”
BackgroundMethodRP-Net: A 3D Convolutional Neural Network for Brain Segmentation From Magnetic Resonance Imaging
Wang, L., Xie, C., & Zeng, N. (2019) · IEEE Access · doi:10.1109/access.2019.2906890 · Cited by 50 · cited 2×
“Spatial pyramid pooling [45] Classification, Detection [45] Hand gesture recognition [110], Image steganalysis [146] Brain image segmentation [118] Prostate image segmentation [35] Tumor segmentation for rectal cancer radiotherapy [79] MRI (brain) MRI (prostate) MRI, CT (rectum)”
MethodTask-Driven Feature Pooling for Image Classification
Xie, G.-S., Zhang, X.-Y., Shu, X., Yan, S., & Liu, C. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.140 · Cited by 48 · cited 2×
“Since GMP is an unsupervised representation learning, in Task-Driven Feature pooling [133] GMP was extended to supervised learning, where the ‘pooled’ representations are learned jointly with a classifier to maximize the classification accuracy and showed improved accuracy over the traditional max and average pooling…”
MethodHierarchical Adaptive Pooling by Capturing High-Order Dependency for Graph Representation Learning
Liu, N., Jian, S., Li, D., Zhang, Y., Lai, Z., & Xu, H. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3133646 · Cited by 44 · cited 2×
“Graph classification [125] – – Hierarchical adaptive pooling [74] Graph classification, Graph Matching, Graph Similarity Learning [74] – – Higher-order pooling [19] Action recognition [19] – – Detachable second-order pooling [66] Classification [66] – – [20] Witter identification and document classification [20] – – Adapti…”
MethodKernelized Subspace Pooling for Deep Local Descriptors
Wei, X., Zhang, Y., Gong, Y., & Zheng, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00200 · Cited by 40 · cited 2×
“Kernelized subspace pooling [128] was proposed to obtain a highly invariant description (invariant to flipping, rotation, etc.”
BackgroundHigher-Order Pooling of CNN Features via Kernel Linearization for Action Recognition
Cherian, A., Koniusz, P., & Gould, S. J. (2017) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2017.22 · Cited by 40
Generalized Orderless Pooling Performs Implicit Salient Matching
Simon, M., Gao, Y., Darrell, T., Denzler, J., & Rodner, E. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.531 · Cited by 39 · cited 2×
“The formulation of the a-pooling [102] allows for a continuous transition between average and bilinear pooling by the introduction of a trainable parameter a.”
BackgroundA sparsity-based stochastic pooling mechanism for deep convolutional neural networks
Song, Z., Liu, Y., Song, R., Chen, Z., Yang, J., Zhang, C., & Jiang, Q. Y. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.05.015 · Cited by 39 · cited 2×
“…Fractional max pooling [39] Classification [39] Retinopathy image classification [40] Retina Sparsity-based stochastic pooling [104] Classification [104] – – EasyConvPooling (ECP) [100] Classification [ Pooling to encode spatial or structural information Spatial pyramid pooling [45] Classification,…”
BackgroundLearnable Dynamic Temporal Pooling for Time Series Classification
Lee, D., Lee, S., & Yu, H. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i9.17008 · Cited by 38
Diabetic Retinopathy Classification Using an Efficient Convolutional Neural Network
Gao, J., Leung, C., & Miao, C. (2019) · IEEE International Conference on Agents (ICA) · doi:10.1109/agents.2019.8929191 · Cited by 37
Building Detail-Sensitive Semantic Segmentation Networks With Polynomial Pooling
Wei, Z., Zhang, J., Liu, L., Zhu, F., Shen, F., Zhou, Y., Liu, S., Sun, Y., & Shao, L. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00728 · Cited by 37 · cited 8×
“Rank-based stochastic pooling [101] Classification [101] Abnormal breast identification [148] Breast Mixed pooling [139] Classification [139] Brain tumor segmentation [10] MRI (brain) Hybrid pooling [112] Classification Fractional max pooling [39] Classification [39] Retinopathy image classification [40] Retina Sparsity-bas…”
BackgroundMethodInfluentialLearnable Pooling in Graph Convolutional Networks for Brain Surface Analysis
Gopinath, K. K., Desrosiers, C., & Lombaert, H. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3028391 · Cited by 36
Second-order Temporal Pooling for Action Recognition
Cherian, A., & Gould, S. J. (2018) · International Journal of Computer Vision · doi:10.1007/s11263-018-1111-5 · Cited by 34 · cited 2×
“Global gated Mixture of Second-Order Pooling (GM-SOP) [119] Classification [119] – – Second-order temporal pooling [18] Action recognition [18] – –”
BackgroundHEp-2 Cell Classification Using K-Support Spatial Pooling in Deep CNNs
Han, X., Lei, J., & Chen, Y. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46976-8_1 · Cited by 31 · cited 1×
“Various approaches [30, 43, 45, 91, 92, 115, 117, 130, 136, 145] have been proposed to encode local structure information in the pooled representation.”
BackgroundImages as sets of locally weighted features
de Campos, T. E., Csurka, G., & Perronnin, F. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2011.07.011 · Cited by 29
Global Feature Guided Local Pooling
Kobayashi, T. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00346 · Cited by 27 · cited 6×
“2 In [57] position priors are also added to determine the value of the weights.”
BackgroundMethodInfluentialAdaptive region pooling for object detection
Tsai, Y., Hamsici, O. C., & Yang, M. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298673 · Cited by 27 · cited 1×
“Various approaches [30, 43, 45, 91, 92, 115, 117, 130, 136, 145] have been proposed to encode local structure information in the pooled representation.”
BackgroundGlobal Learnable Pooling With Enhancing Distinctive Feature for Image Classification
Zhang, X., & Zhang, X. (2020) · IEEE Access · doi:10.1109/access.2020.2997078 · Cited by 26 · cited 2×
“Global Learnable Pooling (GLPool) [147] can also be considered as an attention mechanism, where the weight of each pooling location is considered as a parameter and learned together with other network parameters in an end-to-end manner.”
BackgroundAdaptive Graph Convolution Pooling for Brain Surface Analysis
Gopinath, K. K., Desrosiers, C., & Lombaert, H. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20351-1_7 · Cited by 24
A Hybrid Pooling Method for Convolutional Neural Networks
Tong, Z., Aihara, K., & Tanaka, G. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46672-9_51 · Cited by 23 · cited 2×
“Mixed pooling [139] and hybrid pooling [112] introduce randomness in training by randomly selecting either max or average operations for pooling, i.e., where k is a random value to be either 0 or 1 that determines which pooling to be selected, i.e., when k ¼ 1 the max pooling and when k ¼ 0 the…”
BackgroundEncoder-decoder with dense dilated spatial pyramid pooling for prostate MR images segmentation
Geng, L., Wang, J., Xiao, Z., Tong, J., Zhang, F., & Wu, J. (2019) · Computer Assisted Surgery · doi:10.1080/24699322.2019.1649069 · Cited by 22 · cited 2×
“…Classification, Detection [45] Hand gesture recognition [110], Image steganalysis [146] Brain image segmentation [118] Prostate image segmentation [35] Tumor segmentation for rectal cancer radiotherapy [ Action recognition [14] – – Atrous Spatial Pyramid Pooling (ASPP) [12] Segmentation [12]…”
MethodManivannan, S., Cobb, C., Burgess, S., & Trucco, E. (2017) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2017.2653623 · Cited by 21
Self-citationDeep Adaptive Temporal Pooling for Activity Recognition
Song, S., Cheung, N. M., Chandrasekhar, V., & Mandal, B. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240713 · Cited by 19 · cited 1×
“Deep Adaptive Temporal Pooling (DATP) [103] Human activity recognition [103] – –”
BackgroundQi, K., Yang, C., Hu, C., Guan, Q., Tian, W., Shen, S., & Peng, F. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.2968564 · Cited by 13 · cited 3×
“Polycentric circle pooling [92] Remote sensing image recognition.”
BackgroundMethodGated Square-Root Pooling for Image Instance Retrieval
Chen, Z., Lin, J., Chandrasekhar, V., & Duan, L. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451486 · Cited by 12 · cited 1×
“SQUare-root (SQU) pooling [15] Image instance retrieval [15] – –”
ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection
Chen, Z., Zhang, J., Ding, R., & Marculescu, D. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093418 · Cited by 12 · cited 1×
“Virtual Pooling (ViP) [16] Classification, Object Detection [16] – –”
BackgroundZhou, B., Crawford, R., Dogdas, B., Goldmacher, G., & Chen, A. (2019) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2019.00008 · Cited by 12
Nirthika, R., Manivannan, S., & Ramanan, A. (2020) · IEEE International Conference on Industrial and Information Systems (ICIIS) · doi:10.1109/iciis51140.2020.9342711 · Cited by 12
Self-citationLPM: Learnable Pooling Module for Efficient Full-Face Gaze Estimation
Ogusu, R., & Yamanaka, T. (2019) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg.2019.8756523 · Cited by 7 · cited 1×
“Learnable Pooling Module (LPM) [86] Full-face gaze estimation [86] Brain surface analysis [38] MRI (brain) Neural Computing and Applications”
MethodDetachable Second-Order Pooling: Toward High-Performance First-Order Networks
Li, L., Xie, J., Li, P., & Zhang, L. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3052829 · Cited by 6 · cited 1×
“Detachable second-order pooling [66] Classification [66] – –”
Maximal Function Pooling with Applications
Czaja, W., Li, W., Li, Y., & Pekala, M. (2021) · Applied and numerical harmonic analysis · doi:10.1007/978-3-030-69637-5_21 · Cited by 5
Xie, H., Tang, C., Zhang, W., Shen, Y., & Lei, Z. (2020) · Applied Optics · doi:10.1364/ao.409512 · Cited by 4 · cited 1×
“Atrous Spatial Pyramid Pooling (ASPP) [12] Segmentation [12] Multi-scale retinal vessel segmentation [134] Retina”
Hierarchical mix-pooling and its applications to biomedical image classification
Manivannan, S., Wang, R., & Trucco, E. (2016) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2016.7493326 · Cited by 2 · cited 2×
“The Hierarchical Mix-pooling [78] applies max pooling on the average pooled feature maps (and vice versa) to reduce information loss and shows improved performance than applying either max or average pooling alone on the Sparse Coding-based representations.”
MethodSelf-citation
Cited by
Celard, P., Iglesias, E. L., Sorribes-Fdez, J. M., Romero, R., Vieira, A. S., & Borrajo, L. (2023) · Neural Computing and Applications · doi:10.1007/s00521-022-07953-4 · Cited by 188
Mao, C., Xu, J., Rasmussen, L., Li, Y., Adekkanattu, P., Pacheco, J., Bonakdarpour, B., Vassar, R., Shen, L., Jiang, G., et al. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104442 · Cited by 67
Metadata
- Authors
- Nirthika, R., Manivannan, S., Ramanan, A., & Wang, R.
- Venue
- Neural Computing and Applications
- Published
- 2022-02-01
- Volume
- 34
- Issue
- 7
- Pages
- 5321-5347
- ISSN
- 0941-0643 (ISSN-L)
- 1433-3058
- OpenAlex
- W4210813666
- Cited by
- 218
- References
- 123
- FWCI
- 15.46
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.