mlsanityData to 7 Oct 2026

Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization

arXiv 1610.02391 ↗First posted 7 Oct 2016cs.CV cs.AI cs.LGcited by 6,690

Not on the map. Why?

Cited by 263 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose a technique for producing "visual explanations" for decisions from a large class of CNN-based models, making them more transparent. Our approach - Gradient-weighted Class Activation Mapping (Grad-CAM), uses the gradients of any target concept, flowing into the final convolutional layer to produce a coarse localization map highlighting important regions in the image for predicting the concept. Grad-CAM is applicable to a wide variety of CNN model-families: (1) CNNs with fully-connected layers, (2) CNNs used for structured outputs, (3) CNNs used in tasks with multimodal inputs or reinforcement learning, without any architectural changes or re-training. We combine Grad-CAM with fine-grained visualizations to create a high-resolution class-discriminative visualization and apply it to off-the-shelf image classification, captioning, and visual question answering (VQA) models, including ResNet-based architectures. In the context of image classification models, our visualizations (a) lend insights into their failure modes, (b) are robust to adversarial images, (c) outperform previous methods on localization, (d) are more faithful to the underlying model and (e) help achieve generalization by identifying dataset bias. For captioning and VQA, we show that even non-attention based models can localize inputs. We devise a way to identify important neurons through Grad-CAM and combine it with neuron names to provide textual explanations for model decisions. Finally, we design and conduct human studies to measure if Grad-CAM helps users establish appropriate trust in predictions from models and show that Grad-CAM helps untrained users successfully discern a 'stronger' nodel from a 'weaker' one even when both make identical predictions. Our code is available at https://github.com/ramprs/grad-cam/, along with a demo at http://gradcam.cloudcv.org, and a video at youtu.be/COjUB9Izk6E.

Key facts. Cited by 6,690 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Oct 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 1; 2020: 1; 2021: 944; 2022: 1094; 2023: 1241; 2024: 1289; 2025: 1223; 2026: 896.

6,690 papers.

Sort:

By area:

  1. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,612
  2. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  3. 2021FILIP: Fine-grained Interactive Language-Image Pre-Trainingcited by 626
  4. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 591
  5. 2023LERF: Language Embedded Radiance Fieldscited by 538
  6. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  7. 2021MetaFormer Is Actually What You Need for Visioncited by 523
  8. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 501
  9. 2022MONAI: An open-source framework for deep learning in healthcarecited by 438
  10. 2021TransReID: Transformer-based Object Re-Identificationcited by 432
  11. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  12. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
38 more
  1. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generationcited by 376
  2. 2022Visual Language Maps for Robot Navigationcited by 362
  3. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
  4. 2022Prompt-aligned Gradient for Prompt Tuningcited by 339
  5. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  6. 2022Visual Classification via Description from Large Language Modelscited by 331
  7. 2021How Much Can CLIP Benefit Vision-and-Language Tasks?cited by 321
  8. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 316
  9. 2022Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classificationcited by 310
  10. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  11. 2021DyTox: Transformers for Continual Learning with DYnamic TOken eXpansioncited by 291
  12. 2022VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidancecited by 285
  13. 2023On Evaluating Adversarial Robustness of Large Vision-Language Modelscited by 281
  14. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 273
  15. 2021An Empirical Study of Training End-to-End Vision-and-Language Transformerscited by 271
  16. 2022Matryoshka Representation Learningcited by 268
  17. 2021Generalizing Face Forgery Detection with High-frequency Featurescited by 261
  18. 2021Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Conceptscited by 255
  19. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 254
  20. 2022Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baselinecited by 247
  21. 2022Transformers in Medical Imaging: A Surveycited by 245
  22. 2021Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domaincited by 241
  23. 2021Coordinate Attention for Efficient Mobile Network Designcited by 239
  24. 2022What the DAAM: Interpreting Stable Diffusion Using Cross Attentioncited by 233
  25. 2023Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Drivingcited by 231
  26. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 227
  27. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
  28. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 211
  29. 2022Visual Attention Networkcited by 210
  30. 2021Fast Yet Effective Machine Unlearningcited by 209
  31. 2021Vision Transformers are Robust Learnerscited by 208
  32. 2021Trustworthy AI: From Principles to Practicescited by 206
  33. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  34. 2023SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagerycited by 202
  35. 2021Simultaneously Localize, Segment and Rank the Camouflaged Objectscited by 198
  36. 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
  37. 2021General Facial Representation Learning in a Visual-Linguistic Mannercited by 193
  38. 2023Quilt-1M: One Million Image-Text Pairs for Histopathologycited by 192

50 most cited of 6,690 All 6,690 (JSON)