What is the best multi-stage architecture for object recognition?
Open accessThe DOI matches its Crossref record; 56 of the 57 references it cites were found in a registry or an index.
Abstract
In many recent object recognition systems, feature extraction stages are generally composed of a filter bank, a non-linear transformation, and some sort of feature pooling layer. Most systems use only one stage of feature extraction in which the filters are hard-wired, or two stages where the filters in one or both stages are learned in supervised or unsupervised mode. This paper addresses three questions: 1. How does the non-linearities that follow the filter banks influence the recognition accuracy? 2. does learning the filter banks in an unsupervised or supervised manner improve the performance over random filters or hardwired filters? 3. Is there any advantage to using an architecture with two stages of feature extraction, rather than one? We show that using non-linearities that include rectification and local contrast normalization is the single most important ingredient for good accuracy on object recognition benchmarks. We show that two stages of feature extraction yield better accuracy than one. Most surprisingly, we show that a two-stage system with random filters can yield almost 63% recognition rate on Caltech-101, provided that the proper non-linearities and pooling layers are used. Finally, we show that with supervised refinement, the system achieves state-of-the-art performance on NORB dataset (5.6%) and unsupervised pre-training followed by supervised refinement produces good accuracy on Caltech-101 (> 65%), and the lowest known error rate on the undistorted, unprocessed MNIST dataset (0.53%).
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 6×
“Results are presented on the well-known Caltech-101 dataset [7], on the NORB object dataset [15], and on the MNIST dataset of handwritten digits [14].”
BackgroundMethodInfluentialSelf-citationDistinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 10×
“SIFT uses a rectification followed by winner-take-all operation over orientation , which is an extreme form of normalization.”
MethodInfluentialHistograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 3×
“Particular embodiments of the single-stage systems use SIFT features [19, 13], HoG [6], Geometric Blur [5], and models inspired by the architecture of the mammalian primary visual cortex [24], to mention a few.”
MethodReducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Harrison's Principles of Internal Medicine.
(1988) · Annals of Internal Medicine · doi:10.7326/0003-4819-108-3-499_2 · Cited by 12,514
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Lazebnik, S., Schmid, C., & Ponce, J. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.68 · Cited by 7,916 · cited 12×
“The performance of our two-stage system is similar to that of the best single-stage systems based on SIFT and PMK-SVM, perhaps because the PM Kernel is conceptually similar to our feature extractions stage.”
BackgroundMethodInfluentialGreedy layer-wise training of deep networks
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841
Sparse coding with an overcomplete basis set: A strategy employed by V1?
Olshausen, B. A., & Field, D. J. (1997) · Vision Research · doi:10.1016/s0042-6989(97)00169-7 · Cited by 3,642
Linear 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
Fei-Fei, L., Fergus, R., & Perona, P. (2005) · 2004 Conference on Computer Vision and Pattern Recognition Workshop · doi:10.1109/cvpr.2004.383 · Cited by 2,502
Cited by
ImageNet 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
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357
Self-citationSegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2644615 · Cited by 19,631
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839
“For more details of these operations, see (Krizhevsky et al., 2012) and (Jarrett et al., 2009).”
BackgroundRepresentation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001
“Structured sparsity penalties (Kavukcuoglu et al., 2009; Jenatton et al., 2009; Bach et al., 2011; Gregor et al., 2011) could be used for this purpose.”
BackgroundExplaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
“LSTMs (Hochreiter & Schmidhuber, 1997), ReLUs (Jarrett et al., 2009; Glorot et al., 2011), and maxout networks (Good-fellow et al., 2013c) are all intentionally designed to behave in very linear ways, so that they are easier to optimize.”
BackgroundPlaying Atari with Deep Reinforcement Learning
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. (2013) · arXiv · doi:10.48550/arxiv.1312.5602 · Cited by 9,471
“The first hidden layer convolves 16 8× 8 filters with stride 4 with the input image and applies a rectifier nonlinearity [10, 18].”
Self-citationConditional Generative Adversarial Nets
Mirza, M., & Osindero, S. (2014) · arXiv · doi:10.48550/arxiv.1411.1784 · Cited by 8,863
“Both z and y are mapped to hidden layers with Rectified Linear Unit (ReLu) activation [4, 12], with layer sizes 200 and 1000 respectively, before both being mapped to second, combined hidden ReLu layer of dimensionality 1200.”
MethodDeep Learning with Differential Privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978318 · Cited by 6,578
“Previous work has shown that convolutional layers are often transferable: parameters learned from one dataset can be used on another one without retraining [30].”
Background3D Convolutional Neural Networks for Human Action Recognition
Ji, S., Xu, W., Yang, M., & Yu, K. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.59 · Cited by 6,235
How transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061
“Whereas our networks have max pooling and local normalization on layers 1 and 2, just as Jarrett et al. (2009) did, we use a different nonlinearity (relu(x) instead of abs(tanh(x))), different layer sizes and number of layers, as well as other differences.”
BackgroundMethodResultInfluentialThe MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]
Deng, L. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2211477 · Cited by 4,836
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019
“Our method also outperforms by over 20% the two-layer convolutional network of Jarrett et al. (2009), demonstrating the importance of the depth of the network used for our feature.”
MethodNeural Architecture Search with Reinforcement Learning
Zoph, B., & Le, Q. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01578 · Cited by 3,974
“Additionally, it is also possible to predict pooling, local contrast normalization (Jarrett et al., 2009; Krizhevsky et al., 2012), and batchnorm (Ioffe & Szegedy, 2015) in the architectures.”
BackgroundWu, Y., & He, K. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01198-w · Cited by 3,601
“Normalization layers in deep networks had been widely used before the development of BN. Local Response Nor-malization (LRN) [40, 28, 32] was a component in AlexNet [32] and following models [64, 53, 58].”
MethodDeep Convolutional Neural Networks for Image Classification: A Comprehensive Review
Rawat, W., & Wang, Z. (2017) · Neural Computation · doi:10.1162/neco_a_00990 · Cited by 3,503
“DCNN-NN (Jarrett et al., 2009) Dual CNN feature extractor followed by dual neural network 0.”
BackgroundMethodInfluentialEfficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation
Kamnitsas, K., Ledig, C., Newcombe, V. F. J., Simpson, J. P., Kane, A. D., Menon, D. K., Rueckert, D., & Glocker, B. (2017) · Medical Image Analysis · doi:10.1016/j.media.2016.10.004 · Cited by 3,498
“Image intensities were normalized to have zero-mean and unit variance, as it has been reported that this improves CNN results (Jarrett et al. (2009)).”
Striving 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
“…of modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: They use alternating convolution and max-pooling layers followed by a small number of fully connected layers (e.g. Jarrett et al. (2009); Krizhevsky et al. (2012); Ciresan et al.).”
MethodSpectral Normalization for Generative Adversarial Networks
Miyato, T., Kataoka, T., Koyama, M., & Yoshida, Y. (2018) · arXiv · doi:10.48550/arxiv.1802.05957 · Cited by 3,438
Rives, A., Meier, J., Sercu, T., Goyal, S., Lin, Z., Liu, J., Guo, D., Ott, M., Zitnick, C. L., Ma, J., et al. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2016239118 · Cited by 3,286
Brain tumor segmentation with Deep Neural Networks
Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., Pal, C., Jodoin, P.-M., & Larochelle, H. (2017) · Medical Image Analysis · doi:10.1016/j.media.2016.05.004 · Cited by 3,278
“We get the probability of all labels simply by taking the product of each conditional p ( Y | X ) = ij p ( Y ij | X ).”
BackgroundBrain Tumor Segmentation with Deep Neural Networks
Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., Pal, C., Jodoin, P.-M., & Larochelle, H. (2015) · arXiv · doi:10.48550/arxiv.1505.03540 · Cited by 3,278
A survey of deep neural network architectures and their applications
Liu, W., Wang, Z., Liu, X., Zeng, N., Liu, Y., & Alsaadi, F. E. (2017) · Neurocomputing · doi:10.1016/j.neucom.2016.12.038 · Cited by 3,239
A survey of the recent architectures of deep convolutional neural networks
Khan, A., Sohail, A., Zahoora, U., & Qureshi, A. S. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-020-09825-6 · Cited by 3,137
“36 (13) by recalibrating trunk branch , ( ) c i FM T x output thus behaves like a function of a control gate for every neuron output of the trunk branch.”
BackgroundContext-dependent pre-trained deep neural networks for large-vocabulary speech recognition
Dahl, G. E., Yu, D., Deng, L., & Acero, A. (2012) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2011.2134090 · Cited by 3,011
“This semi-supervised approach using deep models has proved effective in a number of applications, including coding and classification for speech, audio, text, and image data ([25]–[29]).”
BackgroundDeep learning and its applications to machine health monitoring
Zhao, R., Yan, R., Chen, Z., Mao, K., Wang, P., & Gao, R. X. (2019) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2018.05.050 · Cited by 2,894
AutoAugment: Learning Augmentation Strategies From Data
Cubuk, E. D., Zoph, B., Mané, D., Vasudevan, V., & Le, Q. V. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00020 · Cited by 2,733
“Network architectures can also be used to hardcode invariances: convolutional networks bake in translation invariance [16, 32, 25, 29].”
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
Miyato, T., Maeda, S.-I., Koyama, M., & Ishii, S. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2858821 · Cited by 2,843
An analysis of single-layer networks in unsupervised feature learning
Coates, A., Ng, A. Y., & Lee, H. (2011) · International Conference on Artificial Intelligence and Statistics · Cited by 4,675
Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images
Pereira, S., Pinto, A., Alves, V., & Silva, C. A. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2538465 · Cited by 2,735
DeepReID: Deep Filter Pairing Neural Network for Person Re-identification
Li, W., Zhao, R., Xiao, T., & Wang, X. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.27 · Cited by 2,611
“Deep learning has achieved great success in solving many computer vision problems, including hand-written digit recognition [22], object recognition [17, 36], object detection [38, 31, 46, 28], image classification [23, 21], scene understanding [8], and face recognition [5, 39, 52, 40].”
BackgroundOverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6229 · Cited by 2,680
“Recognizing the category of the dominant object in an image i s a tasks to which Convolutional Networks (ConvNets) [17] have been applied for many years, w hether the objects were handwritten characters [16], house numbers [24], textureless toys [18] , traffic signs [3, 26], objects from the Caltech-101 dataset [14],…”
BackgroundSelf-citationMethods for interpreting and understanding deep neural networks
Montavon, G., Samek, W., & Müller, K.-R. (2018) · Digital Signal Processing · doi:10.1016/j.dsp.2017.10.011 · Cited by 2,665
“Examples are LSTMs [26], normalization layers [27,33], or improved element-wise nonlinearities [31].”
BackgroundLearning Hierarchical Features for Scene Labeling
Farabet, C., Couprie, C., Najman, L., & LeCun, Y. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.231 · Cited by 2,620
Self-citationEmpirical Asset Pricing via Machine Learning
Gu, S., Kelly, B., & Xiu, D. (2020) · The Review of Financial Studies · doi:10.1093/rfs/hhaa009 · Cited by 2,545
Generative Adversarial Networks
(2022) · The Science of Deep Learning · doi:10.1017/9781108891530.013 · Cited by 2,402
Searching for activation functions
Ramachandran, P., Zoph, B., & Le, Q. V. (2017) · arXiv · doi:10.48550/arxiv.1710.05941 · Cited by 2,335
“Currently, the most successful and widely-used activation function is the Rectified Linear Unit (ReLU) (Hahnloser et al., 2000; Jarrett et al., 2009; Nair & Hinton, 2010), defined as f(x) = max(x, 0).”
MethodProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning
Elnaggar, A., Heinzinger, M., Dallago, C., Rehawi, G., Wang, Y., Jones, L., Gibbs, T., Feher, T., Angerer, C., Steinegger, M., et al. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3095381 · Cited by 2,329
“3 A) or some inductive bias of neural networks [63].”
BackgroundPractical Recommendations for Gradient-Based Training of Deep Architectures
Bengio, Y. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8_26 · Cited by 2,259
“Several non-linearities have been proposed and some choices of non-linearities have been shown to be more successful (Jarrett et al. , 2009; Glorot and Bengio, 2010; Glorot et al. , 2011a).”
BackgroundInfluentialDeep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art
Zhang, L., Zhang, L., & Du, B. (2016) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2016.2540798 · Cited by 2,208
“Finally, objects are assembled into scenes [107], [108].”
BackgroundConvolutional networks and applications in vision
LeCun, Y., Kavukcuoglu, K., & Farabet, C. (2010) · Proceedings of 2010 IEEE International Symposium on Circuits and Systems · doi:10.1109/iscas.2010.5537907 · Cited by 2,213
“In [33], using abs and normalization non-linearities,”
BackgroundSelf-citationDeep Hashing Network for Unsupervised Domain Adaptation
Venkateswara, H., Eusebio, J., Chakraborty, S., & Panchanathan, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.572 · Cited by 2,171
“[35] and MMI [40], digit datasets SVHN [36], USPS and MNIST [28], head pose recognition datasets PIE [33], object recognition datasets COIL [33], Office [42] and Office-Caltech [20].”
Normalization as a canonical neural computation
Carandini, M., & Heeger, D. J. (2012) · Nature Reviews Neuroscience · doi:10.1038/nrn3136 · Cited by 1,906
“Normalization plays an important part in these computer vision systems as it enhances the accuracy of object recognitio”
BackgroundConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders
Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., Kweon, I. S., & Xie, S. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01548 · Cited by 1,791
“Similar to other forms of normalization [42, 45, 68], this step creates a feature competition across channels by mutual inhibition.”
BackgroundHow does the brain solve visual object recognition?
DiCarlo, J. J., Zoccolan, D., & Rust, N. C. (2012) · Neuron · doi:10.1016/j.neuron.2012.01.010 · Cited by 1,790
“Specifically, even with random (non-learned) filter weights, NLN-like models tend to produce easier-to-decode object identity manifolds largely on the strength of the normalization operation (Jarrett et al., 2009; Lewicki and Sejnowski, 2000; Olshausen and Field, 2005; Pinto et al., 2008b), similar in spirit to the ov…”
Deep Learning: Methods and Applications
Deng, L. (2014) · now publishers, Inc. eBooks · doi:10.1561/9781601988157 · Cited by 1,759
Zeiler, M. D., Krishnan, D., Taylor, G. W., & Fergus, R. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539957 · Cited by 1,666
Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
Katz, G., Barrett, C., Dill, D. L., Julian, K., & Kochenderfer, M. J. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-63387-9_5 · Cited by 1,706
“ReLUs are very widely used [22, 24], and it has been suggested that their piecewise linearity allows DNNs to generalize well to previously unseen inputs [6,7,11,26].”
BackgroundBuilding high-level features using large scale unsupervised learning
Le, Q. V. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6639343 · Cited by 1,695
“Next, to achieve invariance to local deformations, we employ local L2 pooling (Hyv¨arinen et al., 2009; Gregor & LeCun, 2010; Le et al., 2010) and lo-cal contrast normalization (Jarrett et al., 2009).”
BackgroundMethodResultInfluentialInvariant Scattering Convolution Networks
Bruna, J., & Mallat, S. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.230 · Cited by 1,633
Lee, C., Xie, S., Gallagher, P., Zhang, Z., & Zhuowen Tu, A. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1409.5185 · Cited by 993
PCANet: A Simple Deep Learning Baseline for Image Classification?
Chan, T.-H., Jia, K., Gao, S., Lu, J., Zeng, Z., & Ma, Y. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2475625 · Cited by 1,362
Dynamic Convolution: Attention Over Convolution Kernels
Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., & Liu, Z. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01104 · Cited by 1,477
“ReLU [24, 16]).”
ISAAC: a convolutional neural network accelerator with in-situ analog arithmetic in crossbars
Shafiee, A., Nag, A., Muralimanohar, N., Balasubramonian, R., Strachan, J. P., Hu, M., Williams, R. S., & Srikumar, V. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001139 · Cited by 1,536
“[28], all of these networks incorporate LRN layers.”
BackgroundDaDianNao: A Machine-Learning Supercomputer
Chen, Y., Luo, T., Liu, S., Zhang, S., He, L., Wang, J., Li, L., Chen, T., Xu, Z., Sun, N., et al. (2014) · 2014 47th Annual IEEE/ACM International Symposium on Microarchitecture · doi:10.1109/micro.2014.58 · Cited by 1,492
“At the same time, the machine-learning domain has profoundly evolved since 2006, where a category of algorithms, called Deep Learning (Convolutional and Deep Neural Networks), has emerged as state-of-the-art across a broad range of applications [33], [28], [32], [34].”
BackgroundDeep learning for computational biology
Angermueller, C., Pärnamaa, T., Parts, L., & Stegle, O. (2016) · Molecular Systems Biology · doi:10.15252/msb.20156651 · Cited by 1,473
“(Li, 2009) in such raw data analysis tasks, for example restoring noisy neural circuitry images (Jain et al , 2007).”
Learning Fast Approximations of Sparse Coding
Gregor, K., & LeCun, Y. (2010) · International Conference on Machine Learning · Cited by 2,401
Self-citationDeep Convolutional Network Cascade for Facial Point Detection
Sun, Y., Wang, X., & Tang, X. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.446 · Cited by 1,382
“Jarrett et al. [14] introduced strong nonlinearities after convolution, including absolute value rectification and local contrast normalization, and also compared different combinations of nonlinearities and pooling strategies .”
BackgroundImproving deep neural networks for LVCSR using rectified linear units and dropout
Dahl, G. E., Sainath, T. N., & Hinton, G. E. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6639346 · Cited by 1,310
“In computer vision research, ReLUs have been used both as activation functions in more standard neural nets and as units in restricted Boltzmann machines (RBMs), where they must be dealt with using approximations since they invalidate the probabilistic model [8, 9, 5].”
MethodEnd-to-end Optimized Image Compression
Ballé, J., Laparra, V., & Simoncelli, E. P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01704 · Cited by 1,275
“Some earlier results suggest that incorporating local normalization in linear block transform coding methods can improve coding performance (Malo et al., 2006), and can improve object recognition performance of cascaded convolutional neural networks (Jarrett et al., 2009).”
ResultLarge-Margin Softmax Loss for Convolutional Neural Networks
Liu, W., Wen, Y., Yu, Z., & Yang, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.02295 · Cited by 408
Adaptive deconvolutional networks for mid and high level feature learning
Zeiler, M. D., Taylor, G. W., & Fergus, R. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126474 · Cited by 1,217
Ahmed, R., Sreeram, V., Mishra, Y., & Arif, M. D. (2020) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2020.109792 · Cited by 1,259
“[229] proposed another novel hybrid model that merges convolution with an AE, and Mathieu et al.”
Method(2011) · doi:10.5591/978-1-57735-516-8/ijcai11-210 · Cited by 1,229
Part-Based R-CNNs for Fine-Grained Category Detection
Zhang, N., Donahue, J., Girshick, R., & Darrell, T. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_54 · Cited by 1,150
“CNNs were popularized by LeCun and colleagues who initially applied such models to digit recognition [28] and OCR [29] and later to generic object recognition tasks [24].”
MethodDeep supervised, but not unsupervised, models may explain IT cortical representation
Khaligh-Razavi, S.-M., & Kriegeskorte, N. (2014) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003915 · Cited by 1,204
A Theoretical Analysis of Feature Pooling in Visual Recognition
Boureau, Y.-L., Ponce, J., & LeCun, Y. (2010) · Cited by 1,660
Self-citationContractive Auto-Encoders: Explicit Invariance During Feature Extraction
Rifai, S., Vincent, P., Muller, X., Glorot, X., & Bengio, Y. (2011) · International Conference on Machine Learning · Cited by 1,603
AutoAugment: Learning Augmentation Policies from Data
Cubuk, E. D., Zoph, B., Mane, D., Vasudevan, V., & Le, Q. V. (2018) · arXiv · doi:10.48550/arxiv.1805.09501 · Cited by 1,106
“Network architectures can also be used to hardcode invariances: convolutional networks bake in translation invariance [3–6], whereas physics models bake in invariance to translations, rotations, and permutations of atoms [7–12].”
BackgroundDeep Learning on Image Denoising: An overview
Tian, C., Fei, L., Zheng, W., Xu, Y., Zuo, W., & Lin, C.-W. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.07.025 · Cited by 1,091
An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
Goodfellow, I. J., Mirza, M., Xiao, D., Courville, A., & Bengio, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6211 · Cited by 1,089
“Rectified linear (Jarrett et al., 2009; Glorot et al., 2011a): et al., 2013): Here g is a gating function. z is divided into disjoint blocks of size k , and g ( i, z ) is 1 if z i is the maximal element of its group.”
BackgroundLearning mid-level features for recognition
Boureau, Y.-L., Bach, F., LeCun, Y., & Ponce, J. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539963 · Cited by 1,052
“Several authors have already stressed the efficiency of max pooling [10, 31], but they have not given theoretical explanations to their findings.”
BackgroundSelf-citationDempster, A., Petitjean, F., & Webb, G. I. (2020) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-020-00701-z · Cited by 982
“Jimenez and Raj (2019) evaluate their method on a selection of binary classification datasets from the UCR archive.”
BackgroundMethodInfluentialAn Insight into Extreme Learning Machines: Random Neurons, Random Features and Kernels
Huang, G.-B. (2014) · Cognitive Computation · doi:10.1007/s12559-014-9255-2 · Cited by 957
“ELM may also be efficient in clustering [55, 77, 78], feature learning [14, 79, 80] and dimensionality reduction.”
BackgroundShiDianNao: shifting vision processing closer to the sensor
Du, Z., Fasthuber, R., Chen, T., Ienne, P., Li, L., Luo, T., Feng, X., Chen, Y., & Temam, O. (2015) · Proceedings of the 42nd Annual International Symposium on Computer Architecture · doi:10.1145/2749469.2750389 · Cited by 933
“Yet, for now, the figure should give the reader a sufficient broad idea of the mapping to follow the development of the architecture in the next section.”
Spiking Deep Convolutional Neural Networks for Energy-Efficient Object Recognition
Cao, Y., Chen, Y., & Khosla, D. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-014-0788-3 · Cited by 917
“Hinton’s work was quickly followed and extended by others (e.g., Bengio 2009; Ranzato et al. 2007 and Jarrett et al. 2009).”
BackgroundMethodTowards better exploiting convolutional neural networks for remote sensing scene classification
Nogueira, K., Penatti, O. A. B., & dos Santos, J. A. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2016.07.001 · Cited by 902
On the use of deep learning for computational imaging
Barbastathis, G., Ozcan, A., & Situ, G. (2019) · Optica · doi:10.1364/optica.6.000921 · Cited by 869
On optimization methods for deep learning
Ngiam, J., Coates, A., Lahiri, A., Prochnow, B., Le, Q. V., & Ng, A. Y. (2011) · International Conference on Machine Learning · Cited by 1,076
PipeLayer: A Pipelined ReRAM-Based Accelerator for Deep Learning
Song, L., Qian, X., Li, H., & Chen, Y. (2017) · 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA) · doi:10.1109/hpca.2017.55 · Cited by 833
“In particular, Artificial Neural Networks techniques as exemplified by deep learning [4, 5, 6] have become the state-of-the-art across a broad range of applications, including object detection [7], scene parsing [8] and visual question answering [9]).”
MethodDeep Learning Hierarchical Representations for Image Steganalysis
Ye, J., Ni, J., & Yi, Y. (2017) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2710946 · Cited by 823
Discriminative Learning of Deep Convolutional Feature Point Descriptors
Simo-Serra, E., Trulls, E., Ferraz, L., Kokkinos, I., Fua, P., & Moreno-Noguer, F. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.22 · Cited by 804
Real-Time Continuous Pose Recovery of Human Hands Using Convolutional Networks
Tompson, J., Stein, M., Lecun, Y., & Perlin, K. (2014) · ACM Transactions on Graphics · doi:10.1145/2629500 · Cited by 801
Self-citationCoupled Dictionary Training for Image Super-Resolution
Yang, J., Wang, Z., Lin, Z., Cohen, S., & Huang, T. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2192127 · Cited by 793
Sequential Deep Learning for Human Action Recognition
Baccouche, M., Mamalet, F., Wolf, C., Garcia, C., & Baskurt, A. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-25446-8_4 · Cited by 782
HCP: A Flexible CNN Framework for Multi-Label Image Classification
Wei, Y., Xia, W., Lin, M., Huang, J., Ni, B., Dong, J., Zhao, Y., & Yan, S. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2491929 · Cited by 784
“Recently, in contrast to the hand-crafted features, learnt image featureswith deep network structures have shown their great potential in various vision recognition tasks [21], [23], [25].”
BackgroundCNN: Single-label to Multi-label
Wei, Y., Xia, W., Huang, J., Ni, B., Dong, J., Zhao, Y., & Yan, S. (2014) · arXiv · doi:10.48550/arxiv.1406.5726 · Cited by 784
“Recently, in contrast to the hand-crafted features, learnt image featureswith deep network structures have shown their great potential in various vision recognition tasks [21], [23], [25].”
BackgroundStochastic Pooling for Regularization of Deep Convolutional Neural Networks
Zeiler, M. D., & Fergus, R. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1301.3557 · Cited by 755
Grounded Compositional Semantics for Finding and Describing Images with Sentences
Socher, R., Karpathy, A., Le, Q. V., Manning, C. D., & Ng, A. Y. (2014) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00177 · Cited by 777
“The layers consist of three sequences of filtering, pooling and local contrast normalization (Jarrett et al., 2009).”
BackgroundMethodDeeplysupervised netsPreprint
Lee, C., Xie, S., Gallagher, P., Zhang, Z., & Tu, Z. (2015) · Cited by 850
ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars
Shafiee, A., Nag, A., Muralimanohar, N., Balasubramonian, R., Strachan, J. P., Hu, M., Williams, R. S., & Srikumar, V. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.12 · Cited by 775
Traffic sign recognition with multi-scale Convolutional Networks
Sermanet, P., & LeCun, Y. (2011) · The 2011 International Joint Conference on Neural Networks · doi:10.1109/ijcnn.2011.6033589 · Cited by 759
“However more sophisticated non-linear modules have recently been shown to yield higher accuracy, particularly in the small training set size regime [9].”
BackgroundSelf-citationDiscriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks
Dosovitskiy, A., Fischer, P., Springenberg, J. T., Riedmiller, M., & Brox, T. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2496141 · Cited by 762
Pedestrian Detection with Unsupervised Multi-stage Feature Learning
Sermanet, P., Kavukcuoglu, K., Chintala, S., & Lecun, Y. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.465 · Cited by 742
Self-citationLearning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks
Zhao, R., Yan, R., Wang, J., & Mao, K. (2017) · Sensors · doi:10.3390/s17020273 · Cited by 741
Deep Learning using Linear Support Vector Machines
Tang, Y. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1306.0239 · Cited by 708
“These include (but not limited to) speech (Mohamed et al., 2009; Dahl et al., 2010) and vision (Jarrett et al., 2009; Ciresan et al., 2011; Rifai et al., 2011a; Krizhevsky et al., 2012).”
BackgroundA tutorial survey of architectures, algorithms, and applications for deep learning
Deng, L. (2014) · APSIPA Transactions on Signal and Information Processing · doi:10.1017/atsip.2013.9 · Cited by 725
Deep Learning in Drug Discovery
Gawehn, E., Hiss, J. A., & Schneider, G. (2016) · Molecular Informatics · doi:10.1002/minf.201501008 · Cited by 723
Adversarial Training Methods for Semi-Supervised Text Classification
Miyato, T., Dai, A. M., & Goodfellow, I. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.07725 · Cited by 179
“The activation function on the hidden layer was ReLU(Jarrett et al., 2009; Nair & Hinton, 2010; Glorot et al., 2011).”
Background
Metadata
- Authors
- Jarrett, K., Kavukcuoglu, K., Ranzato, M. A., & LeCun, Y.
- Affiliations
- Courant Institute of Mathematical Sciences (US)
- ORCID
- LeCun, Yann
- Venue
- 2009 IEEE 12th International Conference on Computer Vision
- Publisher
- IEEE
- Published
- 2009-09
- Pages
- 2146-2153
- OpenAlex
- W2546302380
- Semantic Scholar
- 1f88427d7aa8225e47f946ac41a0667d7b69ac52
- Cited by
- 2,153
- References
- 57
- Citations by year
- 2026: 20 · 2025: 48 · 2024: 82 · 2023: 114 · 2022: 124 · 2021: 194 · 2020: 207 · 2019: 205 · 2018: 211 · 2017: 210 · 2016: 198 · 2015: 162 · 2014: 137 · 2013: 86 · 2012: 69
- FWCI
- 42.18
- Type
- conference paper
- Language
- en
- Open access
- green
- hal.science
- Licence
- cc-by-nc
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- HAL (submittedVersion, cc-by-nc)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Keywords
- object recognition, filter banks, rectification, feature pooling, unsupervised pre-training, Caltech-101, MNIST, image classification
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.