mlsanityData to 7 Oct 2026

SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization

arXiv 2006.14255 ↗First posted 25 Jun 2020cs.CVcited by 46

Not on the map. Why?

Abstract (arXiv)

Interpretation of the underlying mechanisms of Deep Convolutional Neural Networks has become an important aspect of research in the field of deep learning due to their applications in high-risk environments. To explain these black-box architectures there have been many methods applied so the internal decisions can be analyzed and understood. In this paper, built on the top of Score-CAM, we introduce an enhanced visual explanation in terms of visual sharpness called SS-CAM, which produces centralized localization of object features within an image through a smooth operation. We evaluate our method on the ILSVRC 2012 Validation dataset, which outperforms Score-CAM on both faithfulness and localization tasks.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 12; 2023: 8; 2024: 14; 2025: 5; 2026: 2.

46 papers.

Sort:

By area:

  1. 2021F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscalingcited by 26
  2. 2021Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysiscited by 25
  3. 2023Opti-CAM: Optimizing saliency maps for interpretabilitycited by 25
  4. 2022What Makes a Good Explanation?: A Harmonized View of Properties of Explanationscited by 21
  5. 2022Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localizationcited by 13
  6. 2022TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videoscited by 12
  7. 2023ODAM: Gradient-based instance-specific visual explanations for object detectioncited by 12
  8. 2024Explainable Artificial Intelligence for Medical Applications: A Reviewcited by 12
  9. 2022Re-Attention Transformer for Weakly Supervised Object Localizationcited by 11
  10. 2022Poly-CAM: High resolution class activation map for convolutional neural networkscited by 10
  11. 2023Explain To Me: Salience-Based Explainability for Synthetic Face Detection Modelscited by 8
  12. 2023DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localizationcited by 8
34 more
  1. 2023CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videoscited by 7
  2. 2025Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIPcited by 7
  3. 2021Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifierscited by 6
  4. 2024An Explainable Non-local Network for COVID-19 Diagnosiscited by 5
  5. 2021SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Costcited by 4
  6. 2022TSEM: Temporally Weighted Spatiotemporal Explainable Neural Network for Multivariate Time Seriescited by 4
  7. 2023ViT-ReciproCAM: Gradient and Attention-Free Visual Explanations for Vision Transformercited by 4
  8. 2025From Visual Explanations to Counterfactual Explanations with Latent Diffusioncited by 4
  9. 2022Recipro-CAM: Fast gradient-free visual explanations for convolutional neural networkscited by 3
  10. 2024Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial Defensecited by 3
  11. 2022Crown-CAM: Interpretable Visual Explanations for Tree Crown Detection in Aerial Imagescited by 2
  12. 2023Overview of Class Activation Maps for Visualization Explainabilitycited by 2
  13. 2024Exploring Hyperspectral Anomaly Detection with Human Vision: A Small Target Aware Detectorcited by 2
  14. 2024Challenging the Black Box: A Comprehensive Evaluation of Attribution Maps of CNN Applications in Agriculture and Forestrycited by 2
  15. 2024Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videoscited by 2
  16. 2024AdaptGrad: Adaptive Sampling to Reduce Noisecited by 2
  17. 2021Weakly Supervised Visual-Auditory Fixation Prediction with Multigranularity Perceptioncited by 1
  18. 2022Model LEGO: Creating Models Like Disassembling and Assembling Building Blockscited by 1
  19. 2023BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applicationscited by 1
  20. 2024Spinal Osteophyte Detection via Robust Patch Extraction on minimally annotated X-rayscited by 1
  21. 2024MetaDD: Boosting Dataset Distillation with Neural Network Architecture-Invariant Generalizationcited by 1
  22. 2025Explainable Artificial Intelligence in Biomedical Image Analysis: A Comprehensive Surveycited by 1
  23. 2022Conceptor Learning for Class Activation Mappingcited by 0
  24. 2022Augmented Imagefication: A Data-driven Fault Detection Method for Aircraft Air Data Sensorscited by 0
  25. 2022Fault Detection and Classification of Aerospace Sensors using a VGG16-based Deep Neural Networkcited by 0
  26. 2024Dual-Channel Reliable Breast Ultrasound Image Classification Based on Explainable Attribution and Uncertainty Quantificationcited by 0
  27. 2024HistoSegCap: Capsules for Weakly-Supervised Semantic Segmentation of Histological Tissue Type in Whole Slide Imagescited by 0
  28. 2024Tensor Polynomial Additive Modelcited by 0
  29. 2024Axiomatization of Gradient Smoothing in Neural Networkscited by 0
  30. 2024Integrated feature analysis for deep learning interpretation and class activation mapscited by 0
  31. 2025CAMBench-QR : A Structure-Aware Benchmark for Post-Hoc Explanations with QR Understandingcited by 0
  32. 2025SAGE: Saliency-Guided Contrastive Embeddingscited by 0
  33. 2026Fusion-CAM: Integrating Gradient and Region-Based Class Activation Maps for Robust Visual Explanationscited by 0
  34. 2026How Can One Choose the Best CAM-Based Explainability Method for a CNN Model?cited by 0