Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.14630 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914954759634944 |
|---|---|
| author | Kim, Sangwon Ahn, Dasom Ko, Byoung Chul Jang, In-su Kim, Kwang-Ju |
| author_facet | Kim, Sangwon Ahn, Dasom Ko, Byoung Chul Jang, In-su Kim, Kwang-Ju |
| contents | The demand for reliable AI systems has intensified the need for interpretable deep neural networks. Concept bottleneck models (CBMs) have gained attention as an effective approach by leveraging human-understandable concepts to enhance interpretability. However, existing CBMs face challenges due to deterministic concept encoding and reliance on inconsistent concepts, leading to inaccuracies. We propose EQ-CBM, a novel framework that enhances CBMs through probabilistic concept encoding using energy-based models (EBMs) with quantized concept activation vectors (qCAVs). EQ-CBM effectively captures uncertainties, thereby improving prediction reliability and accuracy. By employing qCAVs, our method selects homogeneous vectors during concept encoding, enabling more decisive task performance and facilitating higher levels of human intervention. Empirical results using benchmark datasets demonstrate that our approach outperforms the state-of-the-art in both concept and task accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_14630 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors Kim, Sangwon Ahn, Dasom Ko, Byoung Chul Jang, In-su Kim, Kwang-Ju Computer Vision and Pattern Recognition Artificial Intelligence The demand for reliable AI systems has intensified the need for interpretable deep neural networks. Concept bottleneck models (CBMs) have gained attention as an effective approach by leveraging human-understandable concepts to enhance interpretability. However, existing CBMs face challenges due to deterministic concept encoding and reliance on inconsistent concepts, leading to inaccuracies. We propose EQ-CBM, a novel framework that enhances CBMs through probabilistic concept encoding using energy-based models (EBMs) with quantized concept activation vectors (qCAVs). EQ-CBM effectively captures uncertainties, thereby improving prediction reliability and accuracy. By employing qCAVs, our method selects homogeneous vectors during concept encoding, enabling more decisive task performance and facilitating higher levels of human intervention. Empirical results using benchmark datasets demonstrate that our approach outperforms the state-of-the-art in both concept and task accuracy. |
| title | EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2409.14630 |