Papers › DecomCAM: Advancing Beyond Saliency Maps through Decomposition and Integration

DecomCAM: Advancing Beyond Saliency Maps through Decomposition and Integration

29 May 2024arXiv:2405.18882archive 2025-07-28

Yuguang Yang, Runtang Guo, Sheng Wu, Yimi Wang, Linlin Yang, Bo Fan, Jilong Zhong, Juan Zhang, Baochang Zhang

Interpreting complex deep networks, notably pre-trained vision-language models (VLMs), is a formidable challenge. Current Class Activation Map (CAM) methods highlight regions revealing the model's decision-making basis but lack clear saliency maps and detailed interpretability. To bridge this gap, we propose DecomCAM, a novel decomposition-and-integration method that distills shared patterns from channel activation maps. Utilizing singular value decomposition, DecomCAM decomposes class-discriminative activation maps into orthogonal sub-saliency maps (OSSMs), which are then integrated together based on their contribution to the target concept. Extensive experiments on six benchmarks reveal that DecomCAM not only excels in locating accuracy but also achieves an optimizing balance between interpretability and computational efficiency. Further analysis unveils that OSSMs correlate with discernible object components, facilitating a granular understanding of the model's reasoning. This positions DecomCAM as a potential tool for fine-grained interpretation of advanced deep learning models. The code is avaible at https://github.com/CapricornGuang/DecomCAM.

PaperPDFCode

Code

capricornguang/decomcam officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Computational EfficiencyDecision Making

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DecomCAM

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections