mlsanityData to 7 Oct 2026

Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping

arXiv 2002.11434 ↗First posted 26 Feb 2020cs.CV cs.LG eess.IVcited by 49

Not on the map. Why?

Abstract (arXiv)

Convolutional neural networks have become state-of-the-art in a wide range of image recognition tasks. The interpretation of their predictions, however, is an active area of research. Whereas various interpretation methods have been suggested for image classification, the interpretation of image segmentation still remains largely unexplored. To that end, we propose SEG-GRAD-CAM, a gradient-based method for interpreting semantic segmentation. Our method is an extension of the widely-used Grad-CAM method, applied locally to produce heatmaps showing the relevance of individual pixels for semantic segmentation.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 7; 2023: 13; 2024: 12; 2025: 9; 2026: 2.

49 papers.

Sort:

By area:

  1. 2023ProtoSeg: Interpretable Semantic Segmentation with Prototypical Partscited by 33
  2. 2023R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generationcited by 29
  3. 2022OCTET: Object-aware Counterfactual Explanationscited by 28
  4. 2022A Survey of Explainable Graph Neural Networks: Taxonomy and Evaluation Metricscited by 26
  5. 2021Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentationcited by 24
  6. 2022Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanationscited by 17
  7. 2021Learning Debiased and Disentangled Representations for Semantic Segmentationcited by 16
  8. 2024Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Surveycited by 11
  9. 2023Real-time High-Resolution Neural Network with Semantic Guidance for Crack Segmentationcited by 10
  10. 2021U-Noise: Learnable Noise Masks for Interpretable Image Segmentationcited by 9
  11. 2024XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approachcited by 7
  12. 2024Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentationcited by 7
37 more
  1. 2025Deep Unfolding Multi-modal Image Fusion Network via Attribution Analysiscited by 7
  2. 2024Aggregated Attributions for Explanatory Analysis of 3D Segmentation Modelscited by 5
  3. 2025Learning Metal Microstructural Heterogeneity through Spatial Mapping of Diffraction Latent Space Featurescited by 5
  4. 2024Multi-Scale Grouped Prototypes for Interpretable Semantic Segmentationcited by 4
  5. 2025Comparative and Interpretative Analysis of CNN and Transformer Models in Predicting Wildfire Spread Using Remote Sensing Datacited by 4
  6. 2021Data Uncertainty Guided Noise-aware Preprocessing Of Fingerprintscited by 3
  7. 2023Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learningcited by 3
  8. 2023Trainable Noise Model as an XAI evaluation method: application on Sobol for remote sensing image segmentationcited by 3
  9. 2023Extending CAM-based XAI methods for Remote Sensing Imagery Segmentationcited by 3
  10. 2024Light-weight Retinal Layer Segmentation with Global Reasoningcited by 3
  11. 2024MiSuRe is all you need to explain your image segmentationcited by 3
  12. 2021Sensor-invariant Fingerprint ROI Segmentation Using Recurrent Adversarial Learningcited by 2
  13. 2022Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesiscited by 2
  14. 2023Explaining Multimodal Data Fusion: Occlusion Analysis for Wilderness Mappingcited by 2
  15. 2023Explainable AI for clinical risk prediction: a survey of concepts, methods, and modalitiescited by 2
  16. 2024Leveraging CAM Algorithms for Explaining Medical Semantic Segmentationcited by 2
  17. 2025ASTRA: A Scene-aware TRAnsformer-based model for trajectory predictioncited by 2
  18. 2021Attention W-Net: Improved Skip Connections for better Representationscited by 1
  19. 2022Adversarial samples for deep monocular 6D object pose estimationcited by 1
  20. 2023Swin Deformable Attention Hybrid U-Net for Medical Image Segmentationcited by 1
  21. 2023A 3D deep learning classifier and its explainability when assessing coronary artery diseasecited by 1
  22. 2024Interpreting a Semantic Segmentation Model for Coastline Detectioncited by 1
  23. 2022Swin Transformer coupling CNNs Makes Strong Contextual Encoders for VHR Image Road Extractioncited by 0
  24. 2022Quantification of geogrid lateral restraint using transparent sand and deep learning-based image segmentationcited by 0
  25. 2023EMShepherd: Detecting Adversarial Samples via Side-channel Leakagecited by 0
  26. 2023Dissecting RGB-D Learning for Improved Multi-modal Fusioncited by 0
  27. 2023Gastro-Intestinal Tract Segmentation Using an Explainable 3D Unetcited by 0
  28. 2024Complementary Information Mutual Learning for Multimodality Medical Image Segmentationcited by 0
  29. 2024Instance-level quantitative saliency in multiple sclerosis lesion segmentationcited by 0
  30. 2024Artificial intelligence techniques in inherited retinal diseases: A reviewcited by 0
  31. 2025Reliable Explainability of Deep Learning Spatial-Spectral Classifiers for Improved Semantic Segmentation in Autonomous Drivingcited by 0
  32. 2025Trustworthy AI-based crack-tip segmentation using domain-guided explanationscited by 0
  33. 2025Comparative Study of UNet-based Architectures for Liver Tumor Segmentation in Multi-Phase Contrast-Enhanced Computed Tomographycited by 0
  34. 2025Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusioncited by 0
  35. 2025XAI-Driven Diagnosis of Generalization Failure in State-Space Cerebrovascular Segmentation Models: A Case Study on Domain Shift Between RSNA and TopCoW Datasetscited by 0
  36. 2026Atomic Depth Estimation From Noisy Electron Microscopy Data Via Deep Learningcited by 0
  37. 2026Efficient KernelSHAP Explanations for Patch-based 3D Medical Image Segmentationcited by 0