Learning Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection
The DOI matches its Crossref record; 71 of the 77 references it cites were found in a registry or an index.
Abstract
The performance of object detection has recently been significantly improved due to the powerful features learnt through convolutional neural networks (CNNs). Despite the remarkable success, there are still several major challenges in object detection, including object rotation, within-class diversity, and between-class similarity, which generally degenerate object detection performance. To address these issues, we build up the existing state-of-the-art object detection systems and propose a simple but effective method to train rotation-invariant and Fisher discriminative CNN models to further boost object detection performance. This is achieved by optimizing a new objective function that explicitly imposes a rotation-invariant regularizer and a Fisher discrimination regularizer on the CNN features. Specifically, the first regularizer enforces the CNN feature representations of the training samples before and after rotation to be mapped closely to each other in order to achieve rotation-invariance. The second regularizer constrains the CNN features to have small within-class scatter but large between-class separation. We implement our proposed method under four popular object detection frameworks, including region-CNN (R-CNN), Fast R- CNN, Faster R- CNN, and R- FCN. In the experiments, we comprehensively evaluate the proposed method on the PASCAL VOC 2007 and 2012 data sets and a publicly available aerial image data set. Our proposed methods outperform the existing baseline methods and achieve the state-of-the-art results.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Designing rotation invariant loss functions is a recent popular solution, where a constraint on the detection loss is added so that the feature of rotated objects keeps unchanged [169-171].”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [171]
Citations
Cites
Deep 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 8×
“In Table 10, the baseline method is the combination of R-FCN [5] and ResNet-101 [9].”
InfluentialVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 9×
“In Table 7, the baseline method is the combination of the R-CNN framework [1], [2], VGGNet-16 [13], and bounding box regression (BB).”
InfluentialImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 6×
“We implement our method for aerial car detection within the R-CNN framework and adopt the most popular AlexNet CNN [6], which is pre-trained on ImageNet [7], as our basic network structure.”
InfluentialFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 10×
“To further reduce the computational costs of R-CNN [1], [2] and Fast R-CNN [3], Faster R-CNN [4] was proposed.”
InfluentialFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812 · cited 10×
“To further reduce the computational costs of R-CNN [1], [2] and Fast R-CNN [3], Faster R-CNN [4] was proposed.”
InfluentialImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 7×
“Then, R-CNN extracts CNN features from each object proposal and classifies them as objects or non-objects with class-specific support vector machines (SVMs), where the deep CNN model was pre-trained on ImageNet data set [7] and then fine-tuned on a small set of images annotated for the detection task.”
InfluentialYou Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1×
“More recently, due to the great success of deep convolutional neural networks (CNNs) for image classification [6] on the ImageNet large scale visual recognition challenge (ILSVRC) [7], [8], CNN-based methods for object detection have been attracting increasing research interest because these methods have achieved stat…”
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Research works printed but not linked: 3
- lin, 2013, Network in Network
- he, 2014, Spatial pyramid pooling in deep convolutional networks for visual recognition, Proc Eur Conf Comput Vis, 346
- girshick, 2015, Fast R-CNN, Proc IEEE Int Conf Comput Vis, 1440
Cited by
Object Detection in 20 Years: A Survey
Zou, Z., Chen, K., Shi, Z., Guo, Y., & Ye, J. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3238524 · Cited by 3,689
“Designing rotation invariant loss functions is a recent popular solution, where a constraint on the detection loss is added so that the feature of rotated objects keeps unchanged [169], [170], [171].”
Deep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01247-4 · Cited by 2,965
Object detection in optical remote sensing images: A survey and a new benchmark
Li, K., Wan, G., Cheng, G., Meng, L., & Han, J. (2020) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.11.023 · Cited by 2,317
“, 2017), RIFD‐CNN (with Faster R‐CNN framework) (Cheng et al., 2019), Faster R‐CNN (Ren et al.”
BackgroundMethodInfluentialSelf-citationZheng, Z., Wang, P., Ren, D., Liu, W., Ye, R., Hu, Q., & Zuo, W. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3095305 · Cited by 1,552
Cheng, G., Xie, X., Han, J., Guo, L., & Xia, G.-S. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.3005403 · Cited by 995
Self-citationObject Detection in Aerial Images: A Large-Scale Benchmark and Challenges
Ding, J., Xue, N., Xia, G.-S., Bai, X., Yang, W., Yang, M. Y., Belongie, S., Luo, J., Datcu, M., Pelillo, M., et al. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3117983 · Cited by 678
“in [6], [9], [10] use rotation-invariant convolutional neural Jian Ding and Liangpei Zhang are with the State Key Laboratory LIESMARS, Wuhan University, Wuhan, Hubei 430079, China.”
BackgroundMethodA survey and performance evaluation of deep learning methods for small object detection
Liu, Y., Sun, P., Wergeles, N., & Shang, Y. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.114602 · Cited by 665
ICAFusion: Iterative cross-attention guided feature fusion for multispectral object detection
Shen, J., Chen, Y., Liu, Y., Zuo, X., Fan, H., & Yang, W. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2023.109913 · Cited by 544
Anchor-Free Oriented Proposal Generator for Object Detection
Cheng, G., Wang, J., Li, K., Xie, X., Lang, C., Yao, Y., & Han, J. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3183022 · Cited by 449
“Many latest works [17]–[26] are based on the two-stage framework.”
BackgroundSelf-citationDeep learning for unmanned aerial vehicle-based object detection and tracking: a survey
Wu, X., Li, W., Hong, D., Tao, R., & Du, Q. (2022) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2021.3115137 · Cited by 421
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network
Fan, D.-P., Zhai, Y., Borji, A., Yang, J., & Shao, L. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58610-2_17 · Cited by 342
Xu, Y., Du, B., Zhang, L., Cerra, D., Pato, M., Carmona, E., Prasad, S., Yokoya, N., Hansch, R., & Le Saux, B. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2911113 · Cited by 337
RingMo: A Remote Sensing Foundation Model With Masked Image Modeling
Sun, X., Wang, P., Lu, W., Zhu, Z., Lu, X., He, Q., Li, J., Rong, X., Yang, Z., Chang, H., et al. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3194732 · Cited by 323
Learning Compact and Discriminative Stacked Autoencoder for Hyperspectral Image Classification
Zhou, P., Han, J., Cheng, G., & Zhang, B. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2893180 · Cited by 289
Self-citationOriented objects as pairs of middle lines
Wei, H., Zhang, Y., Chang, Z., Li, H., Wang, H., & Sun, X. (2020) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2020.09.022 · Cited by 256
Cross-Scale Feature Fusion for Object Detection in Optical Remote Sensing Images
Cheng, G., Si, Y., Hong, H., Yao, X., & Guo, L. (2021) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2020.2975541 · Cited by 244
“…targets appear in remote sensing images with arbitrary orientation, some representative approaches are proposed for rotation-invariant object detection, such as rotation-invariant CNN [20], rotation-invariant and Fisher discriminative CNN [21], and rotation-insensitive region proposal network [22].”
BackgroundSelf-citationDeep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2018) · arXiv · doi:10.48550/arxiv.1809.02165 · Cited by 2,965
Mask-Refined R-CNN: A Network for Refining Object Details in Instance Segmentation
Zhang, Y., Chu, J., Leng, L., & Miao, J. (2020) · Sensors · doi:10.3390/s20041010 · Cited by 214
“The other class is based on object detection [32,33].”
BackgroundAziz, L., Haji Salam, M. S. B., Sheikh, U. U., & Ayub, S. (2020) · IEEE Access · doi:10.1109/access.2020.3021508 · Cited by 204
“Furthermore, the author uses the rotation-invariant and fisher discrimination regularity to optimize the new objective function and improve the performance of the existing framework [175].”
MethodHyperspectral Anomaly Detection With Kernel Isolation Forest
Li, S., Zhang, K., Duan, P., & Kang, X. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2936308 · Cited by 205
“research topic in the field of HSI processing [27], [28], and deep learning-based anomaly detector [29] also has been proposed.”
BackgroundRotation-Invariant Attention Network for Hyperspectral Image Classification
Zheng, X., Sun, H., Lu, X., & Xie, W. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3177322 · Cited by 196
Remote Sensing Object Detection Meets Deep Learning: A metareview of challenges and advances
Zhang, X., Zhang, T., Wang, G., Zhu, P., Tang, X., Jia, X., & Jiao, L. (2023) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2023.3312347 · Cited by 177
“To this purpose, many researchers proposed a series of meth-ods for learning the rotational invariance of objects [146], [147], [148], [149], [150], [151], [152], [153], [154], [155], [156], [157], which significantly improves rotated object detection in RSIs.”
BackgroundMethodWang, Q., Huang, W., Xiong, Z., & Li, X. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3042276 · Cited by 185
Zhang, Z., Zhang, L., Wang, Y., Feng, P., & He, R. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3104230 · Cited by 181
Zhang, L., Lan, M., Zhang, J., & Tao, D. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3104032 · Cited by 172
“As the rapid development of deep learning technique, supervised learning-based convolutional neural networks (CNNs) have shown excellent ability of feature extraction and have been applied to many RS image-processing tasks [6]–[10].”
MethodTransformer with Transfer CNN for Remote-Sensing-Image Object Detection
Li, Q., Chen, Y., & Zeng, Y. (2022) · Remote Sensing · doi:10.3390/rs14040984 · Cited by 160
DRBox-v2: An Improved Detector With Rotatable Boxes for Target Detection in SAR Images
An, Q., Pan, Z., Liu, L., & You, H. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2920534 · Cited by 162
“Some CNNbased approaches apply rectangle bounding boxes for this task, while others try to learn rotation-invariant detectors [45]–[47] or employ rotatable bounding box (RBox) [38], [43], [48], which can represent the targets more accurately and exclude the interference of background more effectively, therefore achiev…”
ResultA General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection
Huang, Z., Li, W., Xia, X.-G., & Tao, R. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3148874 · Cited by 179
Prototype-CNN for Few-Shot Object Detection in Remote Sensing Images
Cheng, G., Yan, B., Shi, P., Li, K., Yao, X., Guo, L., & Han, J. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3078507 · Cited by 193
“Moreover, Cheng et al. [16], [37] proposed a rotation-invariant and Fisher discriminative CNN to simultaneously address the challenges of arbitrary orientation, within-class diversity, and between-class similarity.”
BackgroundSelf-citationSmall Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning
Yuan, X., Cheng, G., Yan, K., Zeng, Q., & Han, J. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00581 · Cited by 222
“generic detectors [31, 6, 27, 33, 7, 3, 28, 5] usually struggle on handling small objects due to two inherent challenges: the insufficient and low-quality samples for training and the uncertain prediction of RoIs (Region of Interests).”
BackgroundSelf-citationQu, Z., Mei, J., Liu, L., & Zhou, D. (2020) · IEEE Access · doi:10.1109/access.2020.2981561 · Cited by 158
“This network has a good effect on image classification [34]–[36] etc.”
BackgroundDecoupling and Integration Network for Camouflaged Object Detection
Zhou, X., Wu, Z., & Cong, R. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3360710 · Cited by 167
“…objectdetectionfarexceedstworelatedtasksincludingsalient objectdetection[9],[10],[11],[12],[13],[14],[15]andgeneric objectdetection[16],[17],[18],[19],[20],[21],wherecamou-flagedobjectsshowninFig.1(a)notonlyshareextremelysimilar…”
Multi-level region-based Convolutional Neural Network for image emotion classification
Rao, T., Li, X., Zhang, H., & Xu, M. G. (2019) · Neurocomputing · doi:10.1016/j.neucom.2018.12.053 · Cited by 159
“Therefore, the emotion can be used as an anchor in the detection tasks like saliency detection [49], co-saliency detection [50], and object detection [51, 52] in future research.”
Ou, C., Zhu, H., Shardt, Y. A. W., Ye, L., Yuan, X., Wang, Y., & Yang, C. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3144162 · Cited by 154
High-Quality Proposals for Weakly Supervised Object Detection
Cheng, G., Yang, J., Gao, D., Guo, L., & Han, J. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2987161 · Cited by 153
Self-citationOn Improving Bounding Box Representations for Oriented Object Detection
Yao, Y., Cheng, G., Wang, G., Li, S., Zhou, P., Xie, X., & Han, J. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3231340 · Cited by 163
“1], [2], [3], [4], [5], [6], [7], [8], which is flourishing but challenging.”
Self-citationUncertainty-Guided Cross-Modal Learning for Robust Multispectral Pedestrian Detection
Kim, J. U., Park, S., & Ro, Y. M. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3076466 · Cited by 161
AM³Net: Adaptive Mutual-Learning-Based Multimodal Data Fusion Network
Wang, J., Li, J., Shi, Y., Lai, J., & Tan, X. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3148257 · Cited by 142
Li, W., Wang, Z., Wang, Y., Wu, J., Wang, J., Jia, Y. M., & Gui, G. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.2988477 · Cited by 139
Qian, X., Lin, S., Cheng, G., Yao, X., Ren, H., & Wang, W. (2020) · Remote Sensing · doi:10.3390/rs12010143 · Cited by 129
“These applications may consist of multiple tasks such as scene classification [2–4], object detection [5,6], and other tasks [7–10].”
Self-citationR3-Net: A Deep Network for Multioriented Vehicle Detection in Aerial Images and Videos
Li, Q., Mou, L., Xu, Q., Zhang, Y., & Zhu, X. X. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2895362 · Cited by 129
Fewer is more: efficient object detection in large aerial images
Xie, X., Cheng, G., Li, Q., Miao, S., Li, K., & Han, J. (2023) · Science China Information Sciences · doi:10.1007/s11432-022-3718-5 · Cited by 125
“Driven by convolutional neural networks (CNNs) and advanced detection frameworks [16–28], object detection in aerial images [9, 13, 29–34] has achieved promising results, especially in the directions of rotation-invariant object detection [29–31] and oriented object detection [9–11,14,35–37].”
BackgroundMethodSelf-citationAttention GANs: Unsupervised Deep Feature Learning for Aerial Scene Classification
Yu, Y., Li, X., & Liu, F. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2937830 · Cited by 124
“The general idea of the first group [17], [47]–[50], [54] is to employ full-trained, fine-tuned, or pretrained CNN to extract features from the input scene images, and then feed these features into the classifier such as SVM, extreme learning machine (ELM), and K -nearest neighbor (KNN) for…”
BackgroundDeep learning for processing and analysis of remote sensing big data: a technical review
Zhang, X., Zhou, Y., & Luo, J. (2021) · Big Earth Data · doi:10.1080/20964471.2021.1964879 · Cited by 137
“Cheng, Han, Zhou, and Xu (2019) explicitly imposed a rotation-invariant regularizer and a Fisher discrimination regularizer on the CNN-based feature to further boost object detection performance.”
BackgroundHan, W., Chen, J., Wang, L., Feng, R., Li, F., Wu, L., Tian, T., & Yan, J. (2021) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2020.3041450 · Cited by 126
Cross-Layer Attention Network for Small Object Detection in Remote Sensing Imagery
Li, Y., Huang, Q., Pei, X., Chen, Y., Jiao, L., & Shang, R. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.3046482 · Cited by 127
“One is a two-stage detector [6]– [8] aiming at improving precision, which are based on anchors.”
BackgroundFeature Enhancement Network for Object Detection in Optical Remote Sensing Images
Cheng, G., Lang, C., Wu, M., Xie, X., Yao, X., & Han, J. (2021) · Journal of Remote Sensing · doi:10.34133/2021/9805389 · Cited by 130
Self-citationFeng, X., Han, J., Yao, X., & Cheng, G. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2985989 · Cited by 114
“After that, many deep learning-based methods [10], [30]–[34] addressed object detection problem in a fully supervised manner and achieved significant improvements.”
BackgroundSelf-citationAutomatic Detection of Underwater Small Targets Using Forward-Looking Sonar Images
Zhou, T., Si, J., Wang, L., Xu, C., & Yu, X. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3181417 · Cited by 152
“The real-time detection of underwater targets needs to localize and recognize the targets accurately, and traditional sonar target detection mainly depends on manual work [3], [4].”
BackgroundSelf-Paced Balance Learning for Clinical Skin Disease Recognition
Yang, J., Wu, X., Liang, J., Sun, X., Cheng, M., Rosin, P. L., & Wang, L. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2917524 · Cited by 125
“detection [29]–[32], and other fields [24], [33]–[35], yet the balanced training data are scarce in practical applications.”
BackgroundChen, J., Li, W., Zhu, J., Xu, G., & Deng, M. (2019) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2019.2930462 · Cited by 108
“An effective method was proposed to train rotation-invariant and Fisher discriminative CNN models by optimizing a new objective function that explicitly imposes a rotation-invariant regularizer and a Fisher discrimination regularizer on the CNN features [11].”
MethodEnhancing remote sensing image retrieval using a triplet deep metric learning network
Cao, R., Zhang, Q., Zhu, J., Li, Q., Li, Q., Liu, B., & Qiu, G. (2019) · International Journal of Remote Sensing · doi:10.1080/2150704x.2019.1647368 · Cited by 112
“Consequently, remote sensing image retrieval (RSIR) has received increasing interest in the remote sensing community.”
MethodInfluentialRotation-Oriented Collaborative Self-Supervised Learning for Retinal Disease Diagnosis
Li, X., Hu, X., Qi, X., Yu, L., Zhao, W., Heng, P.-A., & Xing, L. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3075244 · Cited by 105
A Rotational Libra R-CNN Method for Ship Detection
Guo, H., Yang, X., Wang, N., Song, B., & Gao, X. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2969979 · Cited by 113
“…feature fusion network to reduce classification and localization errors, the rotation-invariant and Fisher discriminative CNN (RIFD-CNN) method [28] that introduced a rotation-invariant regularizer to gain rotation-invariant, and a Fisher discrimination regularizer to alleviate within-class…”
MethodFSoD-Net: Full-Scale Object Detection From Optical Remote Sensing Imagery
Wang, G., Zhuang, Y., Chen, H., Liu, X., Zhang, T., Li, L., Dong, S., & Sang, Q. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3064599 · Cited by 121
Adopting deep learning methods for airborne RGB fluvial scene classification
Carbonneau, P. E., Dugdale, S. J., Breckon, T. P., Dietrich, J. T., Fonstad, M. A., Miyamoto, H., & Woodget, A. S. (2020) · Remote Sensing of Environment · doi:10.1016/j.rse.2020.112107 · Cited by 96
Low Rank Component Induced Spatial-Spectral Kernel Method for Hyperspectral Image Classification
Sun, L., Ma, C., Chen, Y., Zheng, Y., Shim, H. J., Wu, Z., & Jeon, B. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2946723 · Cited by 102
Xiao, Y., Wang, X., Zhang, P., Meng, F., & Shao, F. (2020) · Sensors · doi:10.3390/s20195490 · Cited by 107
Multi-modal deep learning for landform recognition
Du, L., You, X., Li, K., Meng, L., Cheng, G., Xiong, L.-Y., & Wang, G. (2019) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.09.018 · Cited by 91
Self-citationGarajeh, M. K., Malakyar, F., Weng, Q., Feizizadeh, B., Blaschke, T., & Lakes, T. (2021) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2021.146253 · Cited by 103
Combining Faster R-CNN and Model-Driven Clustering for Elongated Object Detection
Fang, F., Li, L., Zhu, H., & Lim, J. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2947792 · Cited by 100
“[5]–[7] introduced”
Chen, H., He, X., Teng, Q., Sheriff, R. E., Feng, J., & Xiong, S. (2020) · Physical review. E · doi:10.1103/physreve.101.023305 · Cited by 94
ASSD: Feature Aligned Single-Shot Detection for Multiscale Objects in Aerial Imagery
Xu, T., Sun, X., Diao, W., Zhao, L., Fu, K., & Wang, H. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3089170 · Cited by 102
“According to the study of [56]–[58], future work could detect with the orientated minimal bounding box instead of the present axis-aligned rectangle.”
BackgroundHe, J., Wang, Y., & Liu, H. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3009284 · Cited by 97
“Different from [80] and [88], we formulate the Fisher regularization by integrating the first-and second-order statistics together in the form of the inverse Fisher discriminant.”
MethodOriented Bounding Boxes for Small and Freely Rotated Objects
Zand, M., Etemad, A., & Greenspan, M. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3076050 · Cited by 101
“Cheng et al. [51] incorporated and learned a rotation-IEEE invariant layer into a CNN architecture.”
Subspace Clustering via Good Neighbors
Yang, J., Liang, J., Wang, K., Rosin, P. L., & Yang, M. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2913863 · Cited by 88
“Data clustering, especially SBSC, has been extensively studied in past decades [21], [22], [23], [24], [25], [26], [27].”
BackgroundMa, C., Zhang, Z., Luce, B., Pusateri, S., Xie, B., Rafiei, M. H., & Hu, N. (2020) · npj Computational Materials · doi:10.1038/s41524-020-0309-6 · Cited by 97
Breast cancer detection from histopathology images with deep inception and residual blocks
Singh, S., & Kumar, R. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11775-2 · Cited by 87
“In case of deep learning CNN as well as multi-layered perceptron can be used for better classification result [13] For image classification CNN has proved to be one of the groundbreakings approach, as it extracts feature vector of highlevel and thus helps in better performance of the network [10].”
MethodAI-based object detection latest trends in remote sensing, multimedia and agriculture applications
Nawaz, S. A., Li, J., Bhatti, U. A., Shoukat, M. U., & Ahmad, R. M. (2022) · Frontiers in Plant Science · doi:10.3389/fpls.2022.1041514 · Cited by 98
Lv, Z. Y., Liu, T., Zhang, P., Benediktsson, J. A., Lei, T., & Zhang, X. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2927659 · Cited by 82
Huang, Z., Li, W., Xia, X., Wu, X., Cai, Z., & Tao, R. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3059450 · Cited by 91
“Benefiting from the availability of a large number of RS image resources, many excellent detectors have been successively developed, such as the two-stage detectors RI-CNN [11], RIFD-CNN [12], FADet [13], SCRDet [14], CAD-Net [15] and the one-stage detectors SBL [16], FMSSD [17], and EFR [18].”
MethodCenter-Boundary Dual Attention for Oriented Object Detection in Remote Sensing Images
Liu, S., Zhang, L., Lu, H., & He, Y. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3069056 · Cited by 97
“Cheng et al. [36], [37] proposed rotation-invariant convolutional neural networks to resolve the ambiguous features of rotated objects in remote sensing images.”
BackgroundInstance-Aware Distillation for Efficient Object Detection in Remote Sensing Images
Li, C., Cheng, G., Wang, G., Zhou, P., & Han, J. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3238801 · Cited by 100
Self-citationMulti-Scale Detector for Accurate Vehicle Detection in Traffic Surveillance Data
Kim, K., Kim, P.-K., Chung, Y.-S., & Choi, D.-H. (2019) · IEEE Access · doi:10.1109/access.2019.2922479 · Cited by 85
AVDNet: A Small-Sized Vehicle Detection Network for Aerial Visual Data
Mandal, M., Shah, M., Meena, P., Devi, S., & Vipparthi, S. K. (2020) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2019.2923564 · Cited by 76
“See http://www.ieee.org/publications_standards/publications/rights/index.html for more information. detectors [8], [23]–[25] have been proposed in the literature.”
BackgroundError Bounded Foreground and Background Modeling for Moving Object Detection in Satellite Videos
Zhang, J., Jia, X., & Hu, J. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2953181 · Cited by 84
A dual neural network for object detection in UAV images
Tian, G., Liu, J., & Yang, W. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.03.016 · Cited by 75
Multi-View Scaling Support Vector Machines for Classification and Feature Selection
Xu, J., Han, J., Nie, F., & Li, X. (2019) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2019.2904256 · Cited by 73
“…learning, computer vision tasks, and multimedia fields, such as image classification [1], [2], text categorization [3], sentiment classification [4], co-segmentation [5], object detection [6], [7], [8], [9], event detection [10], co-saliency detection [11], [12], visual tracking [13] and so on.”
BackgroundSelf-citationNovel up-scale feature aggregation for object detection in aerial images
Hu, L., Zhou, J., Gan, Y., Vong, C., & Liu, Q. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.06.011 · Cited by 74
Mumuni, A., & Mumuni, F. (2021) · SN Computer Science · doi:10.1007/s42979-021-00735-0 · Cited by 81
RIC-CNN: Rotation-Invariant Coordinate Convolutional Neural Network
Mo, H., & Zhao, G. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109994 · Cited by 94
Dilated Convolution Neural Network for Remaining Useful Life Prediction
Xu, X. G., Wu, Q., Li, X., & Huang, B. (2019) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4045293 · Cited by 72
A Relation-Augmented Embedded Graph Attention Network for Remote Sensing Object Detection
Tian, S., Kang, L., Xing, X., Tian, J., Fan, C., & Zhang, Y. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3073269 · Cited by 82
“The aim of object detection is to localize different classes of objects and predict their categories, respectively [5].”
BackgroundA Systematic IoU-Related Method: Beyond Simplified Regression for Better Localization
Peng, H., & Yu, S. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3077144 · Cited by 77
“Recently, [15] exploits new losses to address the object rotation problem and the within-class diversity problem.”
BackgroundDetecting Small Objects Using a Channel-Aware Deconvolutional Network
Duan, K., Du, D., Qi, H., & Huang, Q. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2906246 · Cited by 66
Sun, G., Fu, H., Ren, J., Zhang, A., Zabalza, J., Jia, X., & Zhao, H. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3104100 · Cited by 69
“Future works will focus on more efficient implementation of SpaSSA and its new applications in remote sensing image analysis, which include: 1) weakly supervised learning [48], [49] and context-aware learning [50], [51]; 2) various deep learning, including rotation-invariant CNN [52], autoencoders [53] and deep fusion…”
BackgroundInfluentialXue, J., He, D., Liu, M., & Shi, Q. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3198577 · Cited by 68
“Considering the orientation of the rotated geospatial object, Li et al. [25] explored the feasibility of multiangle anchors in RPN to precise capture the object; Cheng et al. [26], [27] proposed to embed a new rotation-invariant CNN (RICNN) model into R-CNN framework for object detection.”
MethodCA-YOLO: Model Optimization for Remote Sensing Image Object Detection
Shen, L., Lang, B., & Song, Z. (2023) · IEEE Access · doi:10.1109/access.2023.3290480 · Cited by 76
“feature improvement [14], [14], [16], [17], contextual infor-”
X-LineNet: Detecting Aircraft in Remote Sensing Images by a Pair of Intersecting Line Segments
Wei, H., Zhang, Y., Wang, B., Yang, Y., Li, H., & Wang, H. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2999082 · Cited by 66
Where to Prune: Using LSTM to Guide Data-Dependent Soft Pruning
Ding, G., Zhang, S., Jia, Z., Zhong, J., & Han, J. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3035028 · Cited by 71
“I N RECENT years, deep convolutional neural network (CNN) has shown a great success in many computer vision applications, such as image classification [1]–[3], semantic segmentation [4], image captioning [5]–[7], and object detection [8]–[10] and recognition [11]–[13].”
BackgroundSelf-citationMultiple Instance Graph Learning for Weakly Supervised Remote Sensing Object Detection
Wang, B., Zhao, Y., & Li, X. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3123231 · Cited by 85
A survey of recent work on fine-grained image classification techniques
Wang, Y., & Wang, Z. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.12.049 · Cited by 64
Task-wise attention guided part complementary learning for few-shot image classification
Cheng, G., Li, R., Lang, C., & Han, J. (2021) · Science China Information Sciences · doi:10.1007/s11432-020-3156-7 · Cited by 65
Self-citationDalarmelina, N. D. V., Teixeira, M. A., & Meneguette, R. I. (2019) · Sensors · doi:10.3390/s20010055 · Cited by 62
Vehicle detection of multi-source remote sensing data using active fine-tuning network
Wu, X., Li, W., Hong, D., Tian, J., Tao, R., & Du, Q. (2020) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2020.06.016 · Cited by 61
“, 2020), many state-of-the-art vehicle detection algorithms in remote sensing (Cheng et al., 2018; Yang et al., 2018; Wu et al., 2019; Kang and Gellert, 2015; Audebert et al., 2017; Gintautas et al., 2009; Wei et al., 2013; Cheng et al., 2020; Wu et al., 2020) have been developed.”
BackgroundMulti-Attention Object Detection Model in Remote Sensing Images Based on Multi-Scale
Ying, X., Wang, Q., Li, X., Yu, M., Jiang, H., Gao, J., Liu, Z.-Q., & Yu, R. (2019) · IEEE Access · doi:10.1109/access.2019.2928522 · Cited by 61
“[5] G. Cheng and J. Han, ‘‘A survey on object detection in optical remote sensing images,’’ ISPRS J. Photogram.”
BackgroundInfluentialRemote Sensing Landslide Recognition Based on Convolutional Neural Network
Wang, Y., Wang, X., & Jian, J. (2019) · Mathematical Problems in Engineering · doi:10.1155/2019/8389368 · Cited by 60
“[21] proposed an architecture of the initial FD-CNN model, in which a new rotation-invariant layer (FCa) and a new Fisher discriminative layer (FCb) are additionally added to the existing CNN models, and Gong et al.”
MethodContextual deconvolution network for semantic segmentation
Fu, J., Liu, J., Li, Y., Bao, Y., Yan, W., Fang, Z., & Lu, H. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2019.107152 · Cited by 62
Wang, G., Guo, J.-M., Chen, Y., Li, Y., & Xu, Q. (2019) · IEEE Access · doi:10.1109/access.2019.2897283 · Cited by 61
“Several state of the art deep leaning based methods [25]–[27] are introduced in this chapter.”
MethodWeakly Supervised Rotation-Invariant Aerial Object Detection Network
Feng, X., Yao, X., Cheng, G., & Han, J. (2022) · 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/cvpr52688.2022.01375 · Cited by 57
“To this end, existing advanced works [2,4,6,13,15,18,22,41] aim to learn rotation-invariant features by designing learnable rotation-sensitive CNNs.”
BackgroundSelf-citation
Metadata
- Authors
- Cheng, G., Han, J., Zhou, P., & Xu, D.
- Affiliations
- Northwestern Polytechnical University (CN)
- The University of Sydney (AU)
- Venue
- IEEE Transactions on Image Processing
- Published
- 2019-01
- Volume
- 28
- Issue
- 1
- Pages
- 265-278
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W2888527098
- Cited by
- 408
- References
- 77
- Citations by year
- 2026: 12 · 2025: 19 · 2024: 26 · 2023: 46 · 2022: 64 · 2021: 77 · 2020: 77 · 2019: 86
- FWCI
- 30.15
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Natural Science Foundation of China (61772425, 61473231, 61790552)
- Natural Science Basic Research Plan in Shaanxi Province of China (2017JM6044, 2018KJXX-029)
- National Aerospace Science Foundation of China (2017ZC53032)
- Fundamental Research Funds for the Central Universities (3102018zy023)
- Australian Research Council (FT180100116)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- object detection, rotation invariance, within-class scatter, Faster R-CNN, R-FCN, aerial images
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.