mlsanityData to 7 Oct 2026

Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

arXiv 1312.6034 ↗First posted 20 Dec 2013cs.CVcited by 2,348

Not on the map. Why?

Cited by 39 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets). We consider two visualisation techniques, based on computing the gradient of the class score with respect to the input image. The first one generates an image, which maximises the class score [Erhan et al., 2009], thus visualising the notion of the class, captured by a ConvNet. The second technique computes a class saliency map, specific to a given image and class. We show that such maps can be employed for weakly supervised object segmentation using classification ConvNets. Finally, we establish the connection between the gradient-based ConvNet visualisation methods and deconvolutional networks [Zeiler et al., 2013].

Key facts. Cited by 2,348 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Dec 2013.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 1; 2021: 419; 2022: 413; 2023: 479; 2024: 433; 2025: 326; 2026: 276.

2,348 papers.

Sort:

By area:

  1. 2023Towards Automated Circuit Discovery for Mechanistic Interpretabilitycited by 700
  2. 2021Knowledge Neurons in Pretrained Transformerscited by 590
  3. 2024Scaling and evaluating sparse autoencoderscited by 530
  4. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generationcited by 376
  5. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 316
  6. 2022VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidancecited by 285
  7. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  8. 2023Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learningcited by 235
  9. 2023Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Drivingcited by 231
  10. 2022Splicing ViT Features for Semantic Appearance Transfercited by 209
  11. 2021Trustworthy AI: From Principles to Practicescited by 206
  12. 2022CRAFT: Concept Recursive Activation FacTorization for Explainabilitycited by 177
38 more
  1. 2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoningcited by 169
  2. 2022The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspectivecited by 156
  3. 2023Protein Design with Guided Discrete Diffusioncited by 154
  4. 2021Explainable artificial intelligence (XAI) in deep learning-based medical image analysiscited by 147
  5. 2023Rich Human Feedback for Text-to-Image Generationcited by 139
  6. 2021Scaling Up Influence Functionscited by 130
  7. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 129
  8. 2023Similarity of Neural Network Models: A Survey of Functional and Representational Measurescited by 128
  9. 2021Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversitycited by 127
  10. 2021IA-RED2: Interpretability-Aware Redundancy Reduction for Vision Transformerscited by 127
  11. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  12. 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 125
  13. 2023Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfercited by 124
  14. 2023Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directionscited by 123
  15. 2021TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localizationcited by 122
  16. 2021Goal Misgeneralization in Deep Reinforcement Learningcited by 122
  17. 2021Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypescited by 120
  18. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  19. 2022Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questionscited by 116
  20. 2024AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformerscited by 116
  21. 2021Salient ImageNet: How to discover spurious features in Deep Learning?cited by 114
  22. 2024Stable Flow: Vital Layers for Training-Free Image Editingcited by 111
  23. 2023A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimationcited by 108
  24. 2021HIVE: Evaluating the Human Interpretability of Visual Explanationscited by 105
  25. 2021Guided Integrated Gradients: An Adaptive Path Method for Removing Noisecited by 102
  26. 2023Interpretability at Scale: Identifying Causal Mechanisms in Alpacacited by 102
  27. 2023Probabilistic Concept Bottleneck Modelscited by 101
  28. 2023Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Surveycited by 101
  29. 2021Do Feature Attribution Methods Correctly Attribute Features?cited by 98
  30. 2021What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methodscited by 98
  31. 2021Improving and Simplifying Pattern Exploiting Trainingcited by 97
  32. 2021Interpretable Image Classification with Differentiable Prototypes Assignmentcited by 97
  33. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 97
  34. 2022Diffusion Visual Counterfactual Explanationscited by 96
  35. 2021Trustworthy AI: A Computational Perspectivecited by 93
  36. 2024ContextCite: Attributing Model Generation to Contextcited by 93
  37. 2022Interpreting Language Models with Contrastive Explanationscited by 91
  38. 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 90

50 most cited of 2,348 All 2,348 (JSON)