AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Deeply Explain CNN Via Hierarchical Decomposition

Ming‐Ming Cheng, Peng-Tao Jiang, Ling-Hao Han, Liang Wang, Philip H. S. Torr

IJCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 16 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use average activation instead of average gradient to score channel contribution (ablation)gAP · ImageNet, T->S5PCC: 0.623 -> 0.985Improved
use average activation instead of maximum activation to score channel contribution (ablation)gAP · ImageNet, T->S5PCC: 0.897 -> 0.985Improved
use average activation instead of maximum gradient to score channel contribution (ablation)gAP · PASCAL VOC, S2->S1PCC: 0.669 -> 0.893Improved
use average activation instead of maximum activation (ablation)gAP · PASCAL VOC, S2->S1PCC: 0.897 -> 0.893No clear effect
replace score-drop ground truth with gAP single backprop for channel contributionsgAP · VGG-16 channel contribution runtimetime per image: 10s -> 50ms, nearly 200x fasterImproved
decompose with top-16 features per layer as sparse surrogate modelgAP hierarchical decomposition · ImageNet (VGG-16)classification accuracy / match rate: top-16 decomposition gives accuracy similar to the original model and consistent predictions on almost all samplesImproved
use gAP to propagate importance of selected channels versus individual-based methods when ablating top channelsgAP · ILSVRC val (VGG-16)accuracy after ablating top channels (lower is better): gAP obtains lower classification accuracy than other individual-based methodsImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy