The DOI matches its Crossref record; 54 of the 54 references it cites were found in a registry or an index.
Interpreting Deep Visual Representations via Network Dissection
Open accessAbstract
The success of recent deep convolutional neural networks (CNNs) depends on learning hidden representations that can summarize the important factors of variation behind the data. In this work, we describe Network Dissection, a method that interprets networks by providing meaningful labels to their individual units. The proposed method quantifies the interpretability of CNN representations by evaluating the alignment between individual hidden units and visual semantic concepts. By identifying the best alignments, units are given interpretable labels ranging from colors, materials, textures, parts, objects and scenes. The method reveals that deep representations are more transparent and interpretable than they would be under a random equivalently powerful basis. We apply our approach to interpret and compare the latent representations of several network architectures trained to solve a wide range of supervised and self-supervised tasks. We then examine factors affecting the network interpretability such as the number of the training iterations, regularizations, different initialization parameters, as well as networks depth and width. Finally we show that the interpreted units can be used to provide explicit explanations of a given CNN prediction for an image. Our results highlight that interpretability is an important property of deep neural networks that provides new insights into what hierarchical structures can learn.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
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
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
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
Densely 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
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
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
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
(2014) · Cited by 33,419
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
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
Representation 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
Learning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428
Self-citationIntriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
Zagoruyko, S., & Komodakis, N. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.87 · Cited by 7,244
Show and tell: A neural image caption generator
Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298935 · Cited by 6,318
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
Context Encoders: Feature Learning by Inpainting
Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., & Efros, A. A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.278 · Cited by 5,691
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2014.131 · Cited by 4,451
Places: A 10 Million Image Database for Scene Recognition
Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., & Torralba, A. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2723009 · Cited by 4,042
Self-citationScene Parsing through ADE20K Dataset
Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.544 · Cited by 3,326
Self-citationSUN database: Large-scale scene recognition from abbey to zoo
Xiao, J., Hays, J., Ehinger, K. A., Oliva, A., & Torralba, A. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539970 · Cited by 3,283
Self-citationDeep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258
Zhang, R., Isola, P., & Efros, A. A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46487-9_40 · Cited by 3,178
Region-based convolutional networks for accurate object detection and segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2437384 · Cited by 2,912
Understanding deep learning requires rethinking generalization
Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2016) · arXiv · doi:10.48550/arxiv.1611.03530 · Cited by 2,838 · cited 1×
“The question of how representations generalize has been investigated by showing that a CNN can easily fit a random labeling of training data even under explicit regularization [22].”
BackgroundUnsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
Noroozi, M., & Favaro, P. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46466-4_5 · Cited by 2,775
Unsupervised Visual Representation Learning by Context Prediction
Doersch, C., Gupta, A., & Efros, A. A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.167 · Cited by 2,629
(2014) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 2,534
Describing Textures in the Wild
Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., & Vedaldi, A. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.461 · Cited by 2,438
(2007) · CaltechAUTHORS (California Institute of Technology) · Cited by 2,274
Invariant visual representation by single neurons in the human brain
Quiroga, R. Q., Reddy, L., Kreiman, G., Koch, C., & Fried, I. (2005) · Nature · doi:10.1038/nature03687 · Cited by 1,988
Understanding deep image representations by inverting them
Mahendran, A., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299155 · Cited by 1,827
Quattoni, A., & Torralba, A. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206537 · Cited by 1,463
Self-citationThe Role of Context for Object Detection and Semantic Segmentation in the Wild
Mottaghi, R., Chen, X., Liu, X., Cho, N.-G., Lee, S.-W., Fidler, S., Urtasun, R., & Yuille, A. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.119 · Cited by 1,438
Network Dissection: Quantifying Interpretability of Deep Visual Representations
Bau, D., Zhou, B., Khosla, A., Oliva, A., & Torralba, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.354 · Cited by 1,389
Self-citationUnsupervised Learning of Visual Representations Using Videos
Wang, X., & Gupta, A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.320 · Cited by 1,005
Object Detectors Emerge in Deep Scene CNNs
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2014) · arXiv · doi:10.48550/arxiv.1412.6856 · Cited by 971
Self-citationGenerating Videos with Scene Dynamics
Vondrick, C., Pirsiavash, H., & Torralba, A. B. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.02612 · Cited by 785
Self-citationShuffle and Learn: Unsupervised Learning Using Temporal Order Verification
Misra, I., Zitnick, C. L., & Hebert, M. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_32 · Cited by 779 · cited 1×
“investigated 12 networks trained for different self-supervised learning tasks: for predicting context (context) [23], solving puzzles (puzzle) [24], predicting ego-motion (egomotion) [25], learning by moving (moving) [26], predicting video frame order (videoorder) [46] or tracking (tracking) [27], detecting object-cen…”
BackgroundLearning Color Names for Real-World Applications
van de Weijer, J., Schmid, C., Verbeek, J., & Larlus, D. (2009) · IEEE Transactions on Image Processing · doi:10.1109/tip.2009.2019809 · Cited by 709
Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction
Zhang, R., Isola, P., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.76 · Cited by 616
Human action recognition by learning bases of action attributes and parts
Yao, B., Jiang, X., Khosla, A., Lin, A. L., Guibas, L., & Fei-Fei, L. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126386 · Cited by 609
Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts
Chen, X., Mottaghi, R., Liu, X., Fidler, S., Urtasun, R., & Yuille, A. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.254 · Cited by 605
Object Detectors Emerge in Deep Scene CNNsPreprint
Zhou, B., Khosla, A., Lapedriza, À., Oliva, A., & Torralba, A. B. (2015) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 523
Self-citationGenerating Videos with Scene Dynamics
Vondrick, C., Pirsiavash, H., & Torralba, A. (2016) · Maryland Shared Open Access Repository · doi:10.13016/m26gih-tnyz · Cited by 441
Self-citationAnalyzing the Performance of Multilayer Neural Networks for Object Recognition
Agrawal, P., Girshick, R., & Malik, J. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10584-0_22 · Cited by 427
Convergent Learning: Do different neural networks learn the same representations?Preprint
Li, Y., Yosinski, J., Clune, J., Lipson, H., & Hopcroft, J. E. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.07543 · Cited by 412
Agrawal, P., Carreira, J., & Malik, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.13 · Cited by 395
Bell, S., Bala, K., & Snavely, N. (2014) · ACM Transactions on Graphics · doi:10.1145/2601097.2601206 · Cited by 380
Ambient Sound Provides Supervision for Visual Learning
Owens, A., Wu, J., McDermott, J. H., Freeman, W. T., & Torralba, A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_48 · Cited by 373
Self-citationLearning Image Representations Tied to Ego-Motion
Jayaraman, D., & Grauman, K. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.166 · Cited by 213
Transitive Invariance for Self-Supervised Visual Representation Learning
Wang, X., He, K., & Gupta, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.149 · Cited by 168
Object-Centric Representation Learning from Unlabeled Videos
Gao, R., Jayaraman, D., & Grauman, K. L. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-54193-8_16 · Cited by 31
Cited by
A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI
Tjoa, E., & Guan, C. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3027314 · Cited by 2,524
Unified Perceptual Parsing for Scene Understanding
Xiao, T., Liu, Y., Zhou, B., Jiang, Y., & Sun, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01228-1_26 · Cited by 2,201
“Nevertheless, since it is originally collected to discover the alignment between visual concepts and hidden units of Convolutional Neural Networks (CNNs) for network interpretability [26,29], we find that samples from different classes are unbalanced.”
BackgroundSelf-citationExplaining Deep Neural Networks and Beyond: A Review of Methods and Applications
Samek, W., Montavon, G., Lapuschkin, S., Anders, C. J., & Muller, K.-R. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3060483 · Cited by 1,477
“Further methods do not seek to explain in terms of input features but in terms of the latent space, where the directions in the latent space code for higher level concepts, such as color, material, object part, or object [17], [18], [205].”
Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing
Monga, V., Li, Y., & Eldar, Y. C. (2021) · IEEE Signal Processing Magazine · doi:10.1109/msp.2020.3016905 · Cited by 1,414
Explainable artificial intelligence: a comprehensive review
Minh, D., Wang, H. X., Li, Y. F., & Nguyen, T. N. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10088-y · Cited by 983
Metadata
- Authors
- Zhou, B., Bau, D., Oliva, A., & Torralba, A.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2019-09-01
- Volume
- 41
- Issue
- 9
- Pages
- 2131-2145
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W2963081790
- Cited by
- 330
- References
- 54
- FWCI
- 19.52
- Type
- journal article
- Language
- en
- Open access
- green
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.