Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911172821778432 |
|---|---|
| author | Xiong, Nuoye Dong, Anqi Wang, Ning Hua, Cong Zhu, Guangming Mei, Lin Shen, Peiyi Zhang, Liang |
| author_facet | Xiong, Nuoye Dong, Anqi Wang, Ning Hua, Cong Zhu, Guangming Mei, Lin Shen, Peiyi Zhang, Liang |
| contents | Recent advances in deep learning have led to increasingly complex models with deeper layers and more parameters, reducing interpretability and making their decisions harder to understand. While many methods explain black-box reasoning, most lack effective interventions or only operate at sample-level without modifying the model itself. To address this, we propose the Concept Bottleneck Model for Enhancing Human-Neural Network Mutual Understanding (CBM-HNMU). CBM-HNMU leverages the Concept Bottleneck Model (CBM) as an interpretable framework to approximate black-box reasoning and communicate conceptual understanding. Detrimental concepts are automatically identified and refined (removed/replaced) based on global gradient contributions. The modified CBM then distills corrected knowledge back into the black-box model, enhancing both interpretability and accuracy. We evaluate CBM-HNMU on various CNN and transformer-based models across Flower-102, CIFAR-10, CIFAR-100, FGVC-Aircraft, and CUB-200, achieving a maximum accuracy improvement of 2.64% and a maximum increase in average accuracy across 1.03%. Source code is available at: https://github.com/XiGuaBo/CBM-HNMU. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_22803 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding Xiong, Nuoye Dong, Anqi Wang, Ning Hua, Cong Zhu, Guangming Mei, Lin Shen, Peiyi Zhang, Liang Computer Vision and Pattern Recognition Human-Computer Interaction Machine Learning Recent advances in deep learning have led to increasingly complex models with deeper layers and more parameters, reducing interpretability and making their decisions harder to understand. While many methods explain black-box reasoning, most lack effective interventions or only operate at sample-level without modifying the model itself. To address this, we propose the Concept Bottleneck Model for Enhancing Human-Neural Network Mutual Understanding (CBM-HNMU). CBM-HNMU leverages the Concept Bottleneck Model (CBM) as an interpretable framework to approximate black-box reasoning and communicate conceptual understanding. Detrimental concepts are automatically identified and refined (removed/replaced) based on global gradient contributions. The modified CBM then distills corrected knowledge back into the black-box model, enhancing both interpretability and accuracy. We evaluate CBM-HNMU on various CNN and transformer-based models across Flower-102, CIFAR-10, CIFAR-100, FGVC-Aircraft, and CUB-200, achieving a maximum accuracy improvement of 2.64% and a maximum increase in average accuracy across 1.03%. Source code is available at: https://github.com/XiGuaBo/CBM-HNMU. |
| title | Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding |
| topic | Computer Vision and Pattern Recognition Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2506.22803 |