Pith. sign in

REVIEW 7 cited by

Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2011.08891 v4 pith:QNEKVOPD submitted 2020-11-17 eess.IV cs.CVcs.LG

classification eess.IVcs.CVcs.LG
keywords explanationhirescamgrad-cammodelneuralconvolutionaldevelopmentexplanations
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Explanation methods facilitate the development of models that learn meaningful concepts and avoid exploiting spurious correlations. We illustrate a previously unrecognized limitation of the popular neural network explanation method Grad-CAM: as a side effect of the gradient averaging step, Grad-CAM sometimes highlights locations the model did not actually use. To solve this problem, we propose HiResCAM, a novel class-specific explanation method that is guaranteed to highlight only the locations the model used to make each prediction. We prove that HiResCAM is a generalization of CAM and explore the relationships between HiResCAM and other gradient-based explanation methods. Experiments on PASCAL VOC 2012, including crowd-sourced evaluations, illustrate that while HiResCAM's explanations faithfully reflect the model, Grad-CAM often expands the attention to create bigger and smoother visualizations. Overall, this work advances convolutional neural network explanation approaches and may aid in the development of trustworthy models for sensitive applications.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A Diagnostic Gap Framework for Evaluating Reconstruction Fidelity in Weakly Supervised Mammography

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Diagnostic loss in reconstructed mammography ROIs tracks perceptual reconstruction fidelity: autoencoder-level fidelity preserves decisions and explanations, while low-fidelity SDEdit diffusion destroys both and pushe...

  2. Divisive Decisions: Improving Salience-Based Training for Generalization in Binary Classification Tasks

    cs.CV 2025-07 conditional novelty 6.0 of 10

    Teaching binary classifiers to contrast their true-class and false-class attention maps during training yields modest out-of-domain generalization gains, but results are inconsistent and lack significance testing.

  3. Position: Explanation Stability Is a Property of the Model Method Pair, Not the Model

    cs.CV 2026-07 conditional novelty 5.0 of 10

    On chest X-rays, LayerCAM ranks InceptionV3 as the most stable model but Grad-CAM++ ranks DenseNet201 first, showing explanation stability is a property of the model-method pair.

  4. Local Additive Feature Attribution: A Mathematical Taxonomy and Reporting Checklist

    cs.LG 2026-07 accept novelty 5.0 of 10

    Local additive feature-attribution methods are only interpretable relative to stated choices about value functions, baselines, paths, perturbation distributions, and conservation rules.

  5. Automated identification of Ichneumonoidea wasps via YOLO-based deep learning: Integrating HiresCam for Explainable AI

    cs.CV 2026-03 conditional novelty 5.0 of 10

    A YOLOv26 classifier reaches 96% accuracy on 11 Hymenoptera families, and HiResCAM maps link its decisions to traditional taxonomic traits.

  6. Explaining Digital Pathology Models via Clustering Activations

    cs.CV 2025-11 conditional novelty 4.0 of 10

    Clustering a CNN's activation vectors with NMF yields morphological tissue classes that track the model's cancer predictions.

  7. Explainable Artificial Intelligence in Biomedical Image Analysis: A Comprehensive Survey

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A broad modality-aware survey of explainable AI methods for biomedical imaging, covering heatmap, concept, text, and latent-space approaches plus tools, metrics, and vision-language models.

Pith tools