AI Paper Atlas

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

Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding

Nuoye Xiong, Anqi Dong, Ning Wang, Cong Hua, Guangming Zhu, Lin Mei, Peiyi Shen, Liang Zhang

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Concept bottleneck models · 1 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
add CBM-HNMU black-box interventionNFResNet50 · CIFAR-10test accuracy (%): 80.92 -> 83.56Improved
add CBM-HNMU black-box interventionNFResNet50 · CIFAR-100test accuracy (%): 73.58 -> 73.92No clear effect
add CBM-HNMU black-box interventionViT-Small · CIFAR-100test accuracy (%): 81.26 -> 82.43Improved
add CBM-HNMU black-box interventionGCVit · Flower-102test accuracy (%): 93.58 -> 95.20Improved
add CBM-HNMU black-box interventionResNeXt26 · Flower-102test accuracy (%): 88.47 -> 90.85Improved
add CBM-HNMU black-box interventionBotNet26 · FGVC-Aircrafttest accuracy (%): 53.70 -> 54.51Improved
select intervention concepts by class-level gradient instead of randomly (ablation)CBM-HNMU · Flower-102 (NFResNet50)test accuracy (%): 94.72 -> 95.36Improved
select intervention concepts by class-level gradient instead of randomly (ablation)CBM-HNMU · FGVC-Aircraft (ViT-Small)test accuracy (%): 69.97 -> 70.94Improved
use CBM-HNMU instead of CBMCBM · CUB-200 (NFResNet50)test accuracy (%): 54.53 -> 62.67Improved
use CBM-HNMU instead of Post-hoc CBMPost-hoc CBM · CUB-200 (NFResNet50)test accuracy (%): 58.20 -> 62.67Improved
add black-box residual connection to CBM (Post-hoc CBM)CBM · Flower-102 (NFResNet50)test accuracy (%): 92.57 -> 93.58Improved
intervene on all classes instead of fewer than 25% confused classes (ablation)CBM-HNMU · Flower-102, CUB-200, FGVC-Aircraftapproximation bias and accuracy gainHurt

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