--- title: "Grad-CAM: Visual Explanations from Deep — Selvaraju 2016" description: "Convolutional networks perform well across vision tasks, but their internal reasoning is opaque, so it is hard to see why a prediction was made." authors: ["Ramprasaath R. Selvaraju", "Michael Cogswell", "Abhishek Das", "Ramakrishna Vedantam", "Devi Parikh", "Dhruv Batra"] year: 2016 venue: "arXiv:1610.02391" source: "https://arxiv.org/abs/1610.02391" doi: "10.1007/s11263-019-01228-7" arxiv: "1610.02391" licence: "arXiv — non-exclusive license to distribute" licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/selvaraju-2016-grad-cam-visual-explanations-deep/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/selvaraju-2016-grad-cam-visual-explanations-deep/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2016](https://md.research.elamur.ai/free/en/papers/2016/page/2/) / Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization # Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization **Authors:** Ramprasaath R. Selvaraju, [Michael Cogswell](https://md.research.elamur.ai/free/en/authors/michael-cogswell/), Abhishek Das, [Ramakrishna Vedantam](https://md.research.elamur.ai/free/en/authors/ramakrishna-vedantam/), [Devi Parikh](https://md.research.elamur.ai/free/en/authors/devi-parikh/), [Dhruv Batra](https://md.research.elamur.ai/free/en/authors/dhruv-batra/) · **Year:** 2016 · **Venue:** arXiv:1610.02391 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/) **Links:** [Publisher's page](https://doi.org/10.1007/s11263-019-01228-7) · [PDF](https://arxiv.org/pdf/1610.02391) · [DOI 10.1007/s11263-019-01228-7](https://doi.org/10.1007/s11263-019-01228-7) · [arXiv 1610.02391](https://arxiv.org/abs/1610.02391) · [OpenAlex](https://openalex.org/W2616247523) **Citations:** 6161 citations (openalex-snapshot · 2026-10-14) · [166](#cited-by) in our library, of the 140884 papers whose bibliographies we read ## Summary Convolutional networks perform well across vision tasks, but their internal reasoning is opaque, so it is hard to see why a prediction was made. The authors propose Grad-CAM, a generalization of Class Activation Mapping (CAM). It takes the gradient of a chosen output, such as a class score, a generated caption or a VQA answer, with respect to the feature maps of the last convolutional layer. These gradients are pooled into importance weights, which combine the maps into a coarse heatmap of the image regions that support that output. Unlike CAM, the method works on unmodified, already-trained models, including VGG-style networks with fully-connected layers, captioning, VQA and reinforcement-learning models. Fusing the heatmap with Guided Backpropagation produces Guided Grad-CAM, which is both detailed and class-specific. The paper reports several results: - better weakly-supervised localization on ILSVRC-15; - resistance to adversarial perturbations and higher faithfulness to the model; - usefulness for exposing dataset bias; - human studies in which untrained users could identify the stronger of two models that made the same predictions. The work offers a cheap, broadly applicable way to inspect existing CNNs and to decide how far to trust them. ## Key points - In a modified top-5 pointing game on VGG-16, Grad-CAM scored 70.58%, compared with 60.30% for Excitation Backprop (c-MWP). - Grad-CAM localizes the target well at the final convolutional layer of a 200-layer ResNet (fb.resnet.torch). Localization degrades in earlier residual blocks that follow downsampling, and ResNet-18 and ResNet-50 show the same pattern. - Textual explanations come from combining Grad-CAM neuron importance with neuron names from prior work, demonstrated on VGG-16 trained on Places365. - Applied to Neuraltalk2 and to VQA models with AlexNet, VGG-16 and VGG-19 backbones, Grad-CAM shows that models without attention still focus on relevant regions. - Code is available at github.com/ramprs/grad-cam, with a demo on CloudCV. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Other](https://md.research.elamur.ai/free/en/shelves/other/) ## Cited by Cited by 166 papers of our library cite it (of the 140884 whose bibliographies we read); 7 of them have a page here, 159 not yet. - [Security and Privacy Challenges of Large Language Models: A Survey](https://md.research.elamur.ai/free/en/papers/das-2024-security-privacy-challenges-large-language/) - [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://md.research.elamur.ai/free/en/papers/goyal-2016-making-v-vqa-matter-elevating/) - [A Parameter-Efficient Learning Approach to Arabic Dialect Identification with Pre-Trained General-Purpose Speech Model](https://md.research.elamur.ai/free/en/papers/radhakrishnan-2023-parameter-efficient-learning-approach-arabic/) - [Learning Important Features Through Propagating Activation Differences](https://md.research.elamur.ai/free/en/papers/shrikumar-2017-learning-important-features-through-propagating/) - [ViperGPT: Visual Inference via Python Execution for Reasoning](https://md.research.elamur.ai/free/en/papers/suris-2023-vipergpt-visual-inference-python-execution/) - [Explore Political Discourse with Transformers. Emergent Paradigmatic and Syntagmatic Representations.](https://md.research.elamur.ai/free/en/papers/vanni-2026-explore-political-discourse-transformers-emergent/) - [Representation Engineering: A Top-Down Approach to AI Transparency](https://md.research.elamur.ai/free/en/papers/zou-2023-representation-engineering-top-down-approach/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{selvaraju2016grad, title = {{Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization}}, author = {Selvaraju, Ramprasaath R. and Cogswell, Michael and Das, Abhishek and Vedantam, Ramakrishna and Parikh, Devi and Batra, Dhruv}, year = {2016}, doi = {10.1007/s11263-019-01228-7}, eprint = {1610.02391}, archivePrefix = {arXiv}, url = {https://doi.org/10.1007/s11263-019-01228-7} } ``` - [← previous Globally Normalized Transition-Based Neural Networks](https://md.research.elamur.ai/free/en/papers/andor-2016-globally-normalized-transition-based-neural/) - [next → Habakkuk 2:5a: Denouncing ‘wine’ or ‘wealth’? Contextual readings of the Masoretic text and 1QpHab](https://md.research.elamur.ai/free/en/papers/prinsloo-2016-habakkuk-2-5a-denouncing-wine/) - [↑ back to papers of 2016](https://md.research.elamur.ai/free/en/papers/2016/page/2/) ## References 61 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. A. Agrawal, D. Batra, and D. Parikh. Analyzing the Behavior of Visual Question Answering Models. In EMNLP, 2016. 2 [find](https://scholar.google.com/scholar?q=A%2E+Agrawal%2C+D%2E+Batra%2C+and+D%2E+Parikh%2E+Analyzing+the+Behavior+of+Visual+Question+Answering+Models%2E+In+EMNLP%2C+2016%2E+2) [our card](https://md.research.elamur.ai/free/en/papers/agrawal-2016-analyzing-behavior-visual-question-answering/) 2. H. Agrawal, C. S. Mathialagan, Y. Goyal, N. Chavali, P. Banik, A. Mohapatra, A. Osman, and D. Batra. CloudCV: Large Scale Distributed Computer Vision as a Cloud Service. In Mobile Cloud Visual Media Computing, pages 265–290. Springer, 2015. 1 [find](https://scholar.google.com/scholar?q=H%2E+Agrawal%2C+C%2E+S%2E+Mathialagan%2C+Y%2E+Goyal%2C+N%2E+Chavali%2C+P%2E+Banik%2C+A%2E+Mohapatra%2C+A%2E+Osman%2C+and+D%2E+Batra%2E+CloudCV%3A+Large+Scale+Distributed+Computer+Vision+as+a+Cloud+Service%2E+In+Mobile+Cloud+Visual+Media+C) 3. S. Antol, A. Agrawal, J. Lu, M. Mitchell, D. Batra, C. Lawrence Zitnick, and D. Parikh. VQA: Visual Question Answering. In ICCV, 2015. 1, 2, 10, 12 [find](https://scholar.google.com/scholar?q=S%2E+Antol%2C+A%2E+Agrawal%2C+J%2E+Lu%2C+M%2E+Mitchell%2C+D%2E+Batra%2C+C%2E+Lawrence+Zitnick%2C+and+D%2E+Parikh%2E+VQA%3A+Visual+Question+Answering%2E+In+ICCV%2C+2015%2E+1%2C+2%2C+10%2C+12) 4. D. Bau, B. Zhou, A. Khosla, A. Oliva, and A. Torralba. Network dissection: Quantifying interpretability of deep visual representations. In Computer Vision and Pattern Recognition, 2017. 1, 3, 10 [find](https://scholar.google.com/scholar?q=D%2E+Bau%2C+B%2E+Zhou%2C+A%2E+Khosla%2C+A%2E+Oliva%2C+and+A%2E+Torralba%2E+Network+dissection%3A+Quantifying+interpretability+of+deep+visual+representations%2E+In+Computer+Vision+and+Pattern+Recognition%2C+2017%2E+1%2C+3%2C+10) 5. L. Bazzani, A. Bergamo, D. Anguelov, and L. Torresani. Self-taught object localization with deep networks. In WACV, 2016. 4 [find](https://scholar.google.com/scholar?q=L%2E+Bazzani%2C+A%2E+Bergamo%2C+D%2E+Anguelov%2C+and+L%2E+Torresani%2E+Self%2Dtaught+object+localization+with+deep+networks%2E+In+WACV%2C+2016%2E+4) 6. Y. Bengio, A. Courville, and P. Vincent. Representation learning: A review and new perspectives. IEEE transactions on pattern analysis and machine intelligence, 35(8):1798–1828, 2013. 4 [find](https://scholar.google.com/scholar?q=Y%2E+Bengio%2C+A%2E+Courville%2C+and+P%2E+Vincent%2E+Representation+learning%3A+A+review+and+new+perspectives%2E+IEEE+transactions+on+pattern+analysis+and+machine+intelligence%2C+35%288%29%3A1798%E2%80%931828%2C+2013%2E+4) [our card](https://md.research.elamur.ai/free/en/papers/bengio-2012-representation-learning-review-new-perspectives/) 7. X. Chen, H. Fang, T.-Y. Lin, R. Vedantam, S. Gupta, P. Dollár, and C. L. Zitnick. Microsoft COCO captions: Data Collection and Evaluation Server. arXiv preprint arXiv:1504.00325, 2015. 1, 10 [find](https://scholar.google.com/scholar?q=X%2E+Chen%2C+H%2E+Fang%2C+T%2E%2DY%2E+Lin%2C+R%2E+Vedantam%2C+S%2E+Gupta%2C+P%2E+Doll%C3%A1r%2C+and+C%2E+L%2E+Zitnick%2E+Microsoft+COCO+captions%3A+Data+Collection+and+Evaluation+Server%2E+arXiv+preprint+arXiv%3A1504%2E00325%2C+2015%2E+1%2C+10) [our card](https://md.research.elamur.ai/free/en/papers/chen-2015-microsoft-coco-captions-data-collection/) 8. R. G. Cinbis, J. Verbeek, and C. Schmid. Weakly supervised object localization with multi-fold multiple instance learning. IEEE transactions on pattern analysis and machine intelligence, 2016. 3 [find](https://scholar.google.com/scholar?q=R%2E+G%2E+Cinbis%2C+J%2E+Verbeek%2C+and+C%2E+Schmid%2E+Weakly+supervised+object+localization+with+multi%2Dfold+multiple+instance+learning%2E+IEEE+transactions+on+pattern+analysis+and+machine+intelligence%2C+2016%2E+3) 9. A. Das, H. Agrawal, C. L. Zitnick, D. Parikh, and D. Batra. Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions? In EMNLP, 2016. 12 [find](https://scholar.google.com/scholar?q=A%2E+Das%2C+H%2E+Agrawal%2C+C%2E+L%2E+Zitnick%2C+D%2E+Parikh%2C+and+D%2E+Batra%2E+Human+Attention+in+Visual+Question+Answering%3A+Do+Humans+and+Deep+Networks+Look+at+the+Same+Regions%3F+In+EMNLP%2C+2016%2E+12) 10. A. Das, S. Datta, G. Gkioxari, S. Lee, D. Parikh, and D. Batra. Embodied Question Answering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. 1 [find](https://scholar.google.com/scholar?q=A%2E+Das%2C+S%2E+Datta%2C+G%2E+Gkioxari%2C+S%2E+Lee%2C+D%2E+Parikh%2C+and+D%2E+Batra%2E+Embodied+Question+Answering%2E+In+Proceedings+of+the+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29%2C+2018%2E+1) 11. A. Das, S. Kottur, K. Gupta, A. Singh, D. Yadav, J. M. Moura, D. Parikh, and D. Batra. Visual Dialog. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. 1 [find](https://scholar.google.com/scholar?q=A%2E+Das%2C+S%2E+Kottur%2C+K%2E+Gupta%2C+A%2E+Singh%2C+D%2E+Yadav%2C+J%2E+M%2E+Moura%2C+D%2E+Parikh%2C+and+D%2E+Batra%2E+Visual+Dialog%2E+In+Proceedings+of+the+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29%2C+2017%2E+1) 12. A. Das, S. Kottur, J. M. Moura, S. Lee, and D. Batra. Learning cooperative visual dialog agents with deep reinforcement learning. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017. 1 [find](https://scholar.google.com/scholar?q=A%2E+Das%2C+S%2E+Kottur%2C+J%2E+M%2E+Moura%2C+S%2E+Lee%2C+and+D%2E+Batra%2E+Learning+cooperative+visual+dialog+agents+with+deep+reinforcement+learning%2E+In+Proceedings+of+the+IEEE+International+Conference+on+Computer+Vision) 13. H. de Vries, F. Strub, S. Chandar, O. Pietquin, H. Larochelle, and A. C. Courville. Guesswhat?! visual object discovery through multi-modal dialogue. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. 1 [find](https://scholar.google.com/scholar?q=H%2E+de+Vries%2C+F%2E+Strub%2C+S%2E+Chandar%2C+O%2E+Pietquin%2C+H%2E+Larochelle%2C+and+A%2E+C%2E+Courville%2E+Guesswhat%3F%21+visual+object+discovery+through+multi%2Dmodal+dialogue%2E+In+Proceedings+of+the+IEEE+Conference+on+Computer+) 14. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR, 2009. 2, 6, 14 [find](https://scholar.google.com/scholar?q=J%2E+Deng%2C+W%2E+Dong%2C+R%2E+Socher%2C+L%2E%2DJ%2E+Li%2C+K%2E+Li%2C+and+L%2E+Fei%2DFei%2E+ImageNet%3A+A+Large%2DScale+Hierarchical+Image+Database%2E+In+CVPR%2C+2009%2E+2%2C+6%2C+14) 15. A. Dosovitskiy and T. Brox. Inverting Convolutional Networks with Convolutional Networks. In CVPR, 2015. 3 [find](https://scholar.google.com/scholar?q=A%2E+Dosovitskiy+and+T%2E+Brox%2E+Inverting+Convolutional+Networks+with+Convolutional+Networks%2E+In+CVPR%2C+2015%2E+3) 16. D. Erhan, Y. Bengio, A. Courville, and P. Vincent. Visualizing Higher-layer Features of a Deep Network. University of Montreal, 1341, 2009. 3 [find](https://scholar.google.com/scholar?q=D%2E+Erhan%2C+Y%2E+Bengio%2C+A%2E+Courville%2C+and+P%2E+Vincent%2E+Visualizing+Higher%2Dlayer+Features+of+a+Deep+Network%2E+University+of+Montreal%2C+1341%2C+2009%2E+3) 17. M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results. [http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html](http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html), 2009. 19, 20 [↗](http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html) 18. H. Fang, S. Gupta, F. Iandola, R. K. Srivastava, L. Deng, P. Dollár, J. Gao, X. He, M. Mitchell, J. C. Platt, et al. From Captions to Visual Concepts and Back. In CVPR, 2015. 1 [find](https://scholar.google.com/scholar?q=H%2E+Fang%2C+S%2E+Gupta%2C+F%2E+Iandola%2C+R%2E+K%2E+Srivastava%2C+L%2E+Deng%2C+P%2E+Doll%C3%A1r%2C+J%2E+Gao%2C+X%2E+He%2C+M%2E+Mitchell%2C+J%2E+C%2E+Platt%2C+et+al%2E+From+Captions+to+Visual+Concepts+and+Back%2E+In+CVPR%2C+2015%2E+1) 19. C. Gan, N. Wang, Y. Yang, D.-Y. Yeung, and A. G. Hauptmann. Devnet: A deep event network for multimedia event detection and evidence recounting. In CVPR, 2015. 3 [find](https://scholar.google.com/scholar?q=C%2E+Gan%2C+N%2E+Wang%2C+Y%2E+Yang%2C+D%2E%2DY%2E+Yeung%2C+and+A%2E+G%2E+Hauptmann%2E+Devnet%3A+A+deep+event+network+for+multimedia+event+detection+and+evidence+recounting%2E+In+CVPR%2C+2015%2E+3) 20. H. Gao, J. Mao, J. Zhou, Z. Huang, L. Wang, and W. Xu. Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering. In NIPS, 2015. 1, 10, 12 [find](https://scholar.google.com/scholar?q=H%2E+Gao%2C+J%2E+Mao%2C+J%2E+Zhou%2C+Z%2E+Huang%2C+L%2E+Wang%2C+and+W%2E+Xu%2E+Are+You+Talking+to+a+Machine%3F+Dataset+and+Methods+for+Multilingual+Image+Question+Answering%2E+In+NIPS%2C+2015%2E+1%2C+10%2C+12) 21. R. Girshick, J. Donahue, T. Darrell, and J. Malik. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. In CVPR, 2014. 1 [find](https://scholar.google.com/scholar?q=R%2E+Girshick%2C+J%2E+Donahue%2C+T%2E+Darrell%2C+and+J%2E+Malik%2E+Rich+Feature+Hierarchies+for+Accurate+Object+Detection+and+Semantic+Segmentation%2E+In+CVPR%2C+2014%2E+1) [our card](https://md.research.elamur.ai/free/en/papers/girshick-2013-rich-feature-hierarchies-accurate-object/) 22. I. J. Goodfellow, J. Shlens, and C. Szegedy. Explaining and harnessing adversarial examples. stat, 2015. 9 [find](https://scholar.google.com/scholar?q=I%2E+J%2E+Goodfellow%2C+J%2E+Shlens%2C+and+C%2E+Szegedy%2E+Explaining+and+harnessing+adversarial+examples%2E+stat%2C+2015%2E+9) [our card](https://md.research.elamur.ai/free/en/papers/goodfellow-2014-explaining-harnessing-adversarial-examples/) 23. D. Gordon, A. Kembhavi, M. Rastegari, J. Redmon, D. Fox, and A. Farhadi. Iqa: Visual question answering in interactive environments. arXiv preprint arXiv:1712.03316, 2017. 1 — [arXiv:1712.03316](https://arxiv.org/abs/1712.03316) [find](https://scholar.google.com/scholar?q=D%2E+Gordon%2C+A%2E+Kembhavi%2C+M%2E+Rastegari%2C+J%2E+Redmon%2C+D%2E+Fox%2C+and+A%2E+Farhadi%2E+Iqa%3A+Visual+question+answering+in+interactive+environments%2E+arXiv+preprint+arXiv%3A1712%2E03316%2C+2017%2E+1+%E2%80%94+%5BarXiv%3A1712%2E03316%5D%28https) 24. K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In CVPR, 2016. 1, 2, 13, 21 [find](https://scholar.google.com/scholar?q=K%2E+He%2C+X%2E+Zhang%2C+S%2E+Ren%2C+and+J%2E+Sun%2E+Deep+residual+learning+for+image+recognition%2E+In+CVPR%2C+2016%2E+1%2C+2%2C+13%2C+21) 25. D. Hoiem, Y. Chodpathumwan, and Q. Dai. Diagnosing Error in Object Detectors. In ECCV, 2012. 2 [find](https://scholar.google.com/scholar?q=D%2E+Hoiem%2C+Y%2E+Chodpathumwan%2C+and+Q%2E+Dai%2E+Diagnosing+Error+in+Object+Detectors%2E+In+ECCV%2C+2012%2E+2) 26. P. Jackson. Introduction to Expert Systems. Addison-Wesley Longman Publishing Co., Inc., Boston, MA, USA, 3rd edition, 1998. 2 [find](https://scholar.google.com/scholar?q=P%2E+Jackson%2E+Introduction+to+Expert+Systems%2E+Addison%2DWesley+Longman+Publishing+Co%2E%2C+Inc%2E%2C+Boston%2C+MA%2C+USA%2C+3rd+edition%2C+1998%2E+2) 27. Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell. Caffe: Convolutional Architecture for Fast Feature Embedding. In ACM MM, 2014. 6 [find](https://scholar.google.com/scholar?q=Y%2E+Jia%2C+E%2E+Shelhamer%2C+J%2E+Donahue%2C+S%2E+Karayev%2C+J%2E+Long%2C+R%2E+Girshick%2C+S%2E+Guadarrama%2C+and+T%2E+Darrell%2E+Caffe%3A+Convolutional+Architecture+for+Fast+Feature+Embedding%2E+In+ACM+MM%2C+2014%2E+6) [our card](https://md.research.elamur.ai/free/en/papers/jia-2014-caffe-convolutional-architecture-fast-feature/) 28. E. Johns, O. Mac Aodha, and G. J. Brostow. Becoming the Expert - Interactive Multi-Class Machine Teaching. In CVPR, 2015. 2 [find](https://scholar.google.com/scholar?q=E%2E+Johns%2C+O%2E+Mac+Aodha%2C+and+G%2E+J%2E+Brostow%2E+Becoming+the+Expert+%2D+Interactive+Multi%2DClass+Machine+Teaching%2E+In+CVPR%2C+2015%2E+2) 29. J. Johnson, A. Karpathy, and L. Fei-Fei. DenseCap: Fully Convolutional Localization Networks for Dense Captioning. In CVPR, 2016. 1, 10, 11 [find](https://scholar.google.com/scholar?q=J%2E+Johnson%2C+A%2E+Karpathy%2C+and+L%2E+Fei%2DFei%2E+DenseCap%3A+Fully+Convolutional+Localization+Networks+for+Dense+Captioning%2E+In+CVPR%2C+2016%2E+1%2C+10%2C+11) 30. A. Karpathy. What I learned from competing against a ConvNet on ImageNet. [http://karpathy.github.io/2014/09/02/what-i-learned-from-competing-against-a-convnet-on-imagenet/](http://karpathy.github.io/2014/09/02/what-i-learned-from-competing-against-a-convnet-on-imagenet/), 2014. 2 [↗](http://karpathy.github.io/2014/09/02/what-i-learned-from-competing-against-a-convnet-on-imagenet/) 31. A. Karpathy and L. Fei-Fei. Deep visual-semantic alignments for generating image descriptions. In CVPR, 2015. 10, 11 [find](https://scholar.google.com/scholar?q=A%2E+Karpathy+and+L%2E+Fei%2DFei%2E+Deep+visual%2Dsemantic+alignments+for+generating+image+descriptions%2E+In+CVPR%2C+2015%2E+10%2C+11) [our card](https://md.research.elamur.ai/free/en/papers/karpathy-2014-deep-visual-semantic-alignments-generating/) 32. A. Kolesnikov and C. H. Lampert. Seed, expand and constrain: Three principles for weakly-supervised image segmentation. In ECCV, 2016. 7 [find](https://scholar.google.com/scholar?q=A%2E+Kolesnikov+and+C%2E+H%2E+Lampert%2E+Seed%2C+expand+and+constrain%3A+Three+principles+for+weakly%2Dsupervised+image+segmentation%2E+In+ECCV%2C+2016%2E+7) 33. A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, 2012. 1, 5, 6, 16 [find](https://scholar.google.com/scholar?q=A%2E+Krizhevsky%2C+I%2E+Sutskever%2C+and+G%2E+E%2E+Hinton%2E+Imagenet+classification+with+deep+convolutional+neural+networks%2E+In+NIPS%2C+2012%2E+1%2C+5%2C+6%2C+16) 34. M. Lin, Q. Chen, and S. Yan. Network in network. In ICLR, 2014. 3 [find](https://scholar.google.com/scholar?q=M%2E+Lin%2C+Q%2E+Chen%2C+and+S%2E+Yan%2E+Network+in+network%2E+In+ICLR%2C+2014%2E+3) 35. T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick. Microsoft coco: Common objects in context. In ECCV. 2014. 14, 15 [find](https://scholar.google.com/scholar?q=T%2E%2DY%2E+Lin%2C+M%2E+Maire%2C+S%2E+Belongie%2C+J%2E+Hays%2C+P%2E+Perona%2C+D%2E+Ramanan%2C+P%2E+Doll%C3%A1r%2C+and+C%2E+L%2E+Zitnick%2E+Microsoft+coco%3A+Common+objects+in+context%2E+In+ECCV%2E+2014%2E+14%2C+15) [our card](https://md.research.elamur.ai/free/en/papers/lin-2014-microsoft-coco-common-objects-context/) 36. Z. C. Lipton. The Mythos of Model Interpretability. ArXiv e-prints, June 2016. 2, 3 [find](https://scholar.google.com/scholar?q=Z%2E+C%2E+Lipton%2E+The+Mythos+of+Model+Interpretability%2E+ArXiv+e%2Dprints%2C+June+2016%2E+2%2C+3) 37. J. Long, E. Shelhamer, and T. Darrell. Fully convolutional networks for semantic segmentation. In CVPR, 2015. 1 [find](https://scholar.google.com/scholar?q=J%2E+Long%2C+E%2E+Shelhamer%2C+and+T%2E+Darrell%2E+Fully+convolutional+networks+for+semantic+segmentation%2E+In+CVPR%2C+2015%2E+1) 38. J. Lu, X. Lin, D. Batra, and D. Parikh. Deeper LSTM and normalized CNN Visual Question Answering model. [https://github.com/VT-vision-lab/VQA_LSTM_CNN](https://github.com/VT-vision-lab/VQA_LSTM_CNN), 2015. 12, 13, 15 [↗](https://github.com/VT-vision-lab/VQA_LSTM_CNN) 39. J. Lu, J. Yang, D. Batra, and D. Parikh. Hierarchical question-image co-attention for visual question answering. In NIPS, 2016. 13 [find](https://scholar.google.com/scholar?q=J%2E+Lu%2C+J%2E+Yang%2C+D%2E+Batra%2C+and+D%2E+Parikh%2E+Hierarchical+question%2Dimage+co%2Dattention+for+visual+question+answering%2E+In+NIPS%2C+2016%2E+13) 40. A. Mahendran and A. Vedaldi. Salient deconvolutional networks. In European Conference on Computer Vision, 2016. 3 [find](https://scholar.google.com/scholar?q=A%2E+Mahendran+and+A%2E+Vedaldi%2E+Salient+deconvolutional+networks%2E+In+European+Conference+on+Computer+Vision%2C+2016%2E+3) 41. A. Mahendran and A. Vedaldi. Visualizing deep convolutional neural networks using natural pre-images. International Journal of Computer Vision, pages 1–23, 2016. 3, 4 [find](https://scholar.google.com/scholar?q=A%2E+Mahendran+and+A%2E+Vedaldi%2E+Visualizing+deep+convolutional+neural+networks+using+natural+pre%2Dimages%2E+International+Journal+of+Computer+Vision%2C+pages+1%E2%80%9323%2C+2016%2E+3%2C+4) 42. M. Malinowski, M. Rohrbach, and M. Fritz. Ask your neurons: A neural-based approach to answering questions about images. In ICCV, 2015. 1, 10, 12 [find](https://scholar.google.com/scholar?q=M%2E+Malinowski%2C+M%2E+Rohrbach%2C+and+M%2E+Fritz%2E+Ask+your+neurons%3A+A+neural%2Dbased+approach+to+answering+questions+about+images%2E+In+ICCV%2C+2015%2E+1%2C+10%2C+12) 43. M. Oquab, L. Bottou, I. Laptev, and J. Sivic. Learning and transferring mid-level image representations using convolutional neural networks. In CVPR, 2014. 3, 4 [find](https://scholar.google.com/scholar?q=M%2E+Oquab%2C+L%2E+Bottou%2C+I%2E+Laptev%2C+and+J%2E+Sivic%2E+Learning+and+transferring+mid%2Dlevel+image+representations+using+convolutional+neural+networks%2E+In+CVPR%2C+2014%2E+3%2C+4) 44. M. Oquab, L. Bottou, I. Laptev, and J. Sivic. Is object localization for free? – weakly-supervised learning with convolutional neural networks. In CVPR, 2015. 3 [find](https://scholar.google.com/scholar?q=M%2E+Oquab%2C+L%2E+Bottou%2C+I%2E+Laptev%2C+and+J%2E+Sivic%2E+Is+object+localization+for+free%3F+%E2%80%93+weakly%2Dsupervised+learning+with+convolutional+neural+networks%2E+In+CVPR%2C+2015%2E+3) 45. P. O. Pinheiro and R. Collobert. From image-level to pixel-level labeling with convolutional networks. In CVPR, 2015. 3 [find](https://scholar.google.com/scholar?q=P%2E+O%2E+Pinheiro+and+R%2E+Collobert%2E+From+image%2Dlevel+to+pixel%2Dlevel+labeling+with+convolutional+networks%2E+In+CVPR%2C+2015%2E+3) 46. M. Ren, R. Kiros, and R. Zemel. Exploring models and data for image question answering. In NIPS, 2015. 1, 10, 12 [find](https://scholar.google.com/scholar?q=M%2E+Ren%2C+R%2E+Kiros%2C+and+R%2E+Zemel%2E+Exploring+models+and+data+for+image+question+answering%2E+In+NIPS%2C+2015%2E+1%2C+10%2C+12) 47. M. T. Ribeiro, S. Singh, and C. Guestrin. "Why Should I Trust You?": Explaining the Predictions of Any Classifier. In SIGKDD, 2016. 3, 8 [find](https://scholar.google.com/scholar?q=M%2E+T%2E+Ribeiro%2C+S%2E+Singh%2C+and+C%2E+Guestrin%2E+%22Why+Should+I+Trust+You%3F%22%3A+Explaining+the+Predictions+of+Any+Classifier%2E+In+SIGKDD%2C+2016%2E+3%2C+8) [our card](https://md.research.elamur.ai/free/en/papers/ribeiro-2016-why-should-i-trust-explaining/) 48. R. R. Selvaraju, P. Chattopadhyay, M. Elhoseiny, T. Sharma, D. Batra, D. Parikh, and S. Lee. Choose your neuron: Incorporating domain knowledge through neuron-importance. In Proceedings of the European Conference on Computer Vision (ECCV), pages 526–541, 2018. 3 [find](https://scholar.google.com/scholar?q=R%2E+R%2E+Selvaraju%2C+P%2E+Chattopadhyay%2C+M%2E+Elhoseiny%2C+T%2E+Sharma%2C+D%2E+Batra%2C+D%2E+Parikh%2C+and+S%2E+Lee%2E+Choose+your+neuron%3A+Incorporating+domain+knowledge+through+neuron%2Dimportance%2E+In+Proceedings+of+the+Europea) 49. R. R. Selvaraju, S. Lee, Y. Shen, H. Jin, S. Ghosh, L. Heck, D. Batra, and D. Parikh. Taking a hint: Leveraging explanations to make vision and language models more grounded. In Proceedings of the International Conference on Computer Vision (ICCV), 2019. 3 [find](https://scholar.google.com/scholar?q=R%2E+R%2E+Selvaraju%2C+S%2E+Lee%2C+Y%2E+Shen%2C+H%2E+Jin%2C+S%2E+Ghosh%2C+L%2E+Heck%2C+D%2E+Batra%2C+and+D%2E+Parikh%2E+Taking+a+hint%3A+Leveraging+explanations+to+make+vision+and+language+models+more+grounded%2E+In+Proceedings+of+the+Int) 50. D. Silver, A. Huang, C. J. Maddison, A. Guez, L. Sifre, G. Van Den Driessche, J. Schrittwieser, I. Antonoglou, V. Panneershelvam, M. Lanctot, et al. Mastering the game of go with deep neural networks and tree search. Nature, 529(7587):484–489, 2016. 2 [find](https://scholar.google.com/scholar?q=D%2E+Silver%2C+A%2E+Huang%2C+C%2E+J%2E+Maddison%2C+A%2E+Guez%2C+L%2E+Sifre%2C+G%2E+Van+Den+Driessche%2C+J%2E+Schrittwieser%2C+I%2E+Antonoglou%2C+V%2E+Panneershelvam%2C+M%2E+Lanctot%2C+et+al%2E+Mastering+the+game+of+go+with+deep+neural+networks+) 51. K. Simonyan, A. Vedaldi, and A. Zisserman. Deep inside convolutional networks: Visualising image classification models and saliency maps. CoRR, abs/1312.6034, 2013. 3, 6 [find](https://scholar.google.com/scholar?q=K%2E+Simonyan%2C+A%2E+Vedaldi%2C+and+A%2E+Zisserman%2E+Deep+inside+convolutional+networks%3A+Visualising+image+classification+models+and+saliency+maps%2E+CoRR%2C+abs%2F1312%2E6034%2C+2013%2E+3%2C+6) [our card](https://md.research.elamur.ai/free/en/papers/simonyan-2013-deep-inside-convolutional-networks-visualising/) 52. K. Simonyan and A. Zisserman. Very Deep Convolutional Networks for Large-Scale Image Recognition. In ICLR, 2015. 5, 6, 14, 15, 16 [find](https://scholar.google.com/scholar?q=K%2E+Simonyan+and+A%2E+Zisserman%2E+Very+Deep+Convolutional+Networks+for+Large%2DScale+Image+Recognition%2E+In+ICLR%2C+2015%2E+5%2C+6%2C+14%2C+15%2C+16) [our card](https://md.research.elamur.ai/free/en/papers/simonyan-2014-very-deep-convolutional-networks-large/) 53. J. T. Springenberg, A. Dosovitskiy, T. Brox, and M. A. Riedmiller. Striving for Simplicity: The All Convolutional Net. CoRR, abs/1412.6806, 2014. 2, 3, 6, 14 — [arXiv:1412.6806](https://arxiv.org/abs/1412.6806) [find](https://scholar.google.com/scholar?q=J%2E+T%2E+Springenberg%2C+A%2E+Dosovitskiy%2C+T%2E+Brox%2C+and+M%2E+A%2E+Riedmiller%2E+Striving+for+Simplicity%3A+The+All+Convolutional+Net%2E+CoRR%2C+abs%2F1412%2E6806%2C+2014%2E+2%2C+3%2C+6%2C+14+%E2%80%94+%5BarXiv%3A1412%2E6806%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F) 54. C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826, 2016. 6, 12 [find](https://scholar.google.com/scholar?q=C%2E+Szegedy%2C+V%2E+Vanhoucke%2C+S%2E+Ioffe%2C+J%2E+Shlens%2C+and+Z%2E+Wojna%2E+Rethinking+the+inception+architecture+for+computer+vision%2E+In+Proceedings+of+the+IEEE+conference+on+computer+vision+and+pattern+recognition) 55. O. Vinyals, A. Toshev, S. Bengio, and D. Erhan. Show and tell: A neural image caption generator. In CVPR, 2015. 1, 10, 12 [find](https://scholar.google.com/scholar?q=O%2E+Vinyals%2C+A%2E+Toshev%2C+S%2E+Bengio%2C+and+D%2E+Erhan%2E+Show+and+tell%3A+A+neural+image+caption+generator%2E+In+CVPR%2C+2015%2E+1%2C+10%2C+12) [our card](https://md.research.elamur.ai/free/en/papers/vinyals-2014-show-tell-neural-image-caption/) 56. C. Vondrick, A. Khosla, T. Malisiewicz, and A. Torralba. HOGgles: Visualizing Object Detection Features. ICCV, 2013. 9 [find](https://scholar.google.com/scholar?q=C%2E+Vondrick%2C+A%2E+Khosla%2C+T%2E+Malisiewicz%2C+and+A%2E+Torralba%2E+HOGgles%3A+Visualizing+Object+Detection+Features%2E+ICCV%2C+2013%2E+9) 57. M. D. Zeiler and R. Fergus. Visualizing and understanding convolutional networks. In ECCV, 2014. 2, 3, 4, 6, 8, 10, 14 [find](https://scholar.google.com/scholar?q=M%2E+D%2E+Zeiler+and+R%2E+Fergus%2E+Visualizing+and+understanding+convolutional+networks%2E+In+ECCV%2C+2014%2E+2%2C+3%2C+4%2C+6%2C+8%2C+10%2C+14) [our card](https://md.research.elamur.ai/free/en/papers/zeiler-2013-visualizing-understanding-convolutional-networks/) 58. J. Zhang, Z. Lin, J. Brandt, X. Shen, and S. Sclaroff. Top-down Neural Attention by Excitation Backprop. In ECCV, 2016. 4, 6, 7, 12, 16, 20 [find](https://scholar.google.com/scholar?q=J%2E+Zhang%2C+Z%2E+Lin%2C+J%2E+Brandt%2C+X%2E+Shen%2C+and+S%2E+Sclaroff%2E+Top%2Ddown+Neural+Attention+by+Excitation+Backprop%2E+In+ECCV%2C+2016%2E+4%2C+6%2C+7%2C+12%2C+16%2C+20) 59. B. Zhou, A. Khosla, L. A., A. Oliva, and A. Torralba. Learning Deep Features for Discriminative Localization. In CVPR, 2016. 2, 3, 5, 6, 20 [find](https://scholar.google.com/scholar?q=B%2E+Zhou%2C+A%2E+Khosla%2C+L%2E+A%2E%2C+A%2E+Oliva%2C+and+A%2E+Torralba%2E+Learning+Deep+Features+for+Discriminative+Localization%2E+In+CVPR%2C+2016%2E+2%2C+3%2C+5%2C+6%2C+20) 60. B. Zhou, A. Khosla, À. Lapedriza, A. Oliva, and A. Torralba. Object detectors emerge in deep scene cnns. CoRR, abs/1412.6856, 2014. 10 — [arXiv:1412.6856](https://arxiv.org/abs/1412.6856) [find](https://scholar.google.com/scholar?q=B%2E+Zhou%2C+A%2E+Khosla%2C+%C3%80%2E+Lapedriza%2C+A%2E+Oliva%2C+and+A%2E+Torralba%2E+Object+detectors+emerge+in+deep+scene+cnns%2E+CoRR%2C+abs%2F1412%2E6856%2C+2014%2E+10+%E2%80%94+%5BarXiv%3A1412%2E6856%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1412%2E6856%29) 61. B. Zhou, A. Lapedriza, A. Khosla, A. Oliva, and A. Torralba. Places: A 10 million image database for scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017. 10, 11, 20 [find](https://scholar.google.com/scholar?q=B%2E+Zhou%2C+A%2E+Lapedriza%2C+A%2E+Khosla%2C+A%2E+Oliva%2C+and+A%2E+Torralba%2E+Places%3A+A+10+million+image+database+for+scene+recognition%2E+IEEE+Transactions+on+Pattern+Analysis+and+Machine+Intelligence%2C+2017%2E+10%2C+11%2C+20)