AI Paper Atlas

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

Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector

Xianren Zhang, Dongwon Lee, Suhang Wang

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Feature attribution methods · 2 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
pre-train the detector on full images and keep it fixed, instead of training it on masked-out regions (ablation)COMET · ImageNet-9PxAP: 71.41 -> 76.38Improved
pre-train the detector on full images instead of training it on masked-out regions (ablation)COMET · ImageNet-9accuracy (%): 92.82 -> 94.33Improved
pre-train the detector on full images instead of training it on masked-out regions (ablation)COMET · NICO++accuracy (%): 58.38 -> 56.47Hurt
add the pre-trained detector term on masked-out regions to the selector objectiveCOMET · ImageNet-9classification accuracy: 91.16 -> 94.33Improved
add the detector (versus COMET w/o Detector, where predictor and selector interlock) (ablation)COMET · ImageNet-9accuracyImproved
set the masked-out penalty weight a to 0 (no control on masked-out regions) (ablation)COMET · ImageNet-9PxAPHurt
use COMET instead of existing inherently explainable baselines for noisy NICO++ accuracyCOMET · NICO++ (noisy)accuracy (%): 28.97 -> 33.12Improved
use COMET for localization against best post-hoc baselineCOMET · ImageNet-9PxAP: 60.67 -> 76.38Improved
swap the ResNet18 predictor for a ViT in COMETCOMET · ImageNet-9PxAP: 76.38 -> 69.87Hurt
train COMET on randomized labels (sanity check) (ablation)COMET · an8Flowerarea under IOU curve: 72.5 -> 5.83Hurt
use COMET for fidelity (lower perturbed accuracy) versus other inherent methodsCOMET · ImageNet-9 (top 20% removed)perturbed accuracy (%): 21.48 -> 2.07Improved

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