mlsanityData to 7 Oct 2026

Poly-CAM: High resolution class activation map for convolutional neural networks

arXiv 2204.13359 ↗First posted 28 Apr 2022cs.CV cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

The need for Explainable AI is increasing with the development of deep learning. The saliency maps derived from convolutional neural networks generally fail in localizing with accuracy the image features justifying the network prediction. This is because those maps are either low-resolution as for CAM [Zhou et al., 2016], or smooth as for perturbation-based methods [Zeiler and Fergus, 2014], or do correspond to a large number of widespread peaky spots as for gradient-based approaches [Sundararajan et al., 2017, Smilkov et al., 2017]. In contrast, our work proposes to combine the information from earlier network layers with the one from later layers to produce a high resolution Class Activation Map that is competitive with the previous art in term of insertion-deletion faithfulness metrics, while outperforming it in term of precision of class-specific features localization.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 28 of its 57 references that are in the map. First posted on arXiv 28 Apr 2022.

Builds on

28 of 57 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  9. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  10. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  11. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  12. 2018Sanity Checks for Saliency Mapscited by 1,149
16 more
  1. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  2. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  3. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  4. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 575
  5. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
  6. 2017Interpretation of Neural Networks is Fragilecited by 443
  7. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 359
  8. 2019On the (In)fidelity and Sensitivity for Explanationscited by 309
  9. 2016Not Just a Black Box: Learning Important Features Through Propagating Activation Differencescited by 295
  10. 2018Manipulating and Measuring Model Interpretabilitycited by 256
  11. 2019Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Modelscited by 118
  12. 2020SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localizationcited by 46
  13. 2020Improved anomaly detection by training an autoencoder with skip connections on images corrupted with Stain-shaped noisecited by 39
  14. 2020DenserNet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregationcited by 33
  15. 2020IS-CAM: Integrated Score-CAM for axiomatic-based explanationscited by 29
  16. 2020Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labelscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 3; 2025: 1; 2026: 2.

10 papers.

  1. 2023AME-CAM: Attentive Multiple-Exit CAM for Weakly Supervised Segmentation on MRI Brain Tumorcited by 8
  2. 2024Expected Grad-CAM: Towards gradient faithfulnesscited by 4
  3. 2024Challenging the Black Box: A Comprehensive Evaluation of Attribution Maps of CNN Applications in Agriculture and Forestrycited by 2
  4. 2025NeRF-based Visualization of 3D Cues Supporting Data-Driven Spacecraft Pose Estimationcited by 2
  5. 2022Model-Assisted Labeling via Explainability for Visual Inspection of Civil Infrastructurescited by 0
  6. 2023An Experimental Investigation into the Evaluation of Explainability Methodscited by 0
  7. 2023LIPEx-Locally Interpretable Probabilistic Explanations-To Look Beyond The True Classcited by 0
  8. 2024Adapting Visualization Techniques for Time-Series Anomaly Detection: From Convolutional Neural Networks to Convolutional-Recurrent Neural Networkscited by 0
  9. 2026Attribution Upsampling should Redistribute, Not Interpolatecited by 0
  10. 2026Class Activation Mapping in Explainable Computer Vision: A Method-Centered Review of CNN, Transformer, and Foundation-Model-Era Visual Explanationscited by 0