Semi-supervised Concept Bottleneck Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909543968014336 |
|---|---|
| author | Hu, Lijie Huang, Tianhao Xie, Huanyi Gong, Xilin Ren, Chenyang Hu, Zhengyu Yu, Lu Ma, Ping Wang, Di |
| author_facet | Hu, Lijie Huang, Tianhao Xie, Huanyi Gong, Xilin Ren, Chenyang Hu, Zhengyu Yu, Lu Ma, Ping Wang, Di |
| contents | Concept Bottleneck Models (CBMs) have garnered increasing attention due to their ability to provide concept-based explanations for black-box deep learning models while achieving high final prediction accuracy using human-like concepts. However, the training of current CBMs is heavily dependent on the precision and richness of the annotated concepts in the dataset. These concept labels are typically provided by experts, which can be costly and require significant resources and effort. Additionally, concept saliency maps frequently misalign with input saliency maps, causing concept predictions to correspond to irrelevant input features - an issue related to annotation alignment. To address these limitations, we propose a new framework called SSCBM (Semi-supervised Concept Bottleneck Model). Our SSCBM is suitable for practical situations where annotated data is scarce. By leveraging joint training on both labeled and unlabeled data and aligning the unlabeled data at the concept level, we effectively solve these issues. We proposed a strategy to generate pseudo labels and an alignment loss. Experiments demonstrate that our SSCBM is both effective and efficient. With only 10% labeled data, our model's concept and task accuracy on average across four datasets is only 2.44% and 3.93% lower, respectively, compared to the best baseline in the fully supervised learning setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_18992 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Semi-supervised Concept Bottleneck Models Hu, Lijie Huang, Tianhao Xie, Huanyi Gong, Xilin Ren, Chenyang Hu, Zhengyu Yu, Lu Ma, Ping Wang, Di Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Concept Bottleneck Models (CBMs) have garnered increasing attention due to their ability to provide concept-based explanations for black-box deep learning models while achieving high final prediction accuracy using human-like concepts. However, the training of current CBMs is heavily dependent on the precision and richness of the annotated concepts in the dataset. These concept labels are typically provided by experts, which can be costly and require significant resources and effort. Additionally, concept saliency maps frequently misalign with input saliency maps, causing concept predictions to correspond to irrelevant input features - an issue related to annotation alignment. To address these limitations, we propose a new framework called SSCBM (Semi-supervised Concept Bottleneck Model). Our SSCBM is suitable for practical situations where annotated data is scarce. By leveraging joint training on both labeled and unlabeled data and aligning the unlabeled data at the concept level, we effectively solve these issues. We proposed a strategy to generate pseudo labels and an alignment loss. Experiments demonstrate that our SSCBM is both effective and efficient. With only 10% labeled data, our model's concept and task accuracy on average across four datasets is only 2.44% and 3.93% lower, respectively, compared to the best baseline in the fully supervised learning setting. |
| title | Semi-supervised Concept Bottleneck Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2406.18992 |