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
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.
Forward citations
Cited by 7 Pith papers
-
A Diagnostic Gap Framework for Evaluating Reconstruction Fidelity in Weakly Supervised Mammography
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...
-
Divisive Decisions: Improving Salience-Based Training for Generalization in Binary Classification Tasks
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.
-
Position: Explanation Stability Is a Property of the Model Method Pair, Not the Model
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.
-
Local Additive Feature Attribution: A Mathematical Taxonomy and Reporting Checklist
Local additive feature-attribution methods are only interpretable relative to stated choices about value functions, baselines, paths, perturbation distributions, and conservation rules.
-
Automated identification of Ichneumonoidea wasps via YOLO-based deep learning: Integrating HiresCam for Explainable AI
A YOLOv26 classifier reaches 96% accuracy on 11 Hymenoptera families, and HiResCAM maps link its decisions to traditional taxonomic traits.
-
Explaining Digital Pathology Models via Clustering Activations
Clustering a CNN's activation vectors with NMF yields morphological tissue classes that track the model's cancer predictions.
-
Explainable Artificial Intelligence in Biomedical Image Analysis: A Comprehensive Survey
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.
Discussion (0). Sign in to comment.