Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2510.03767 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908577001635840 |
|---|---|
| author | Dong, Yiheng Lin, Yi Yang, Xin |
| author_facet | Dong, Yiheng Lin, Yi Yang, Xin |
| contents | The transparency of deep learning models is essential for clinical diagnostics. Concept Bottleneck Model provides clear decision-making processes for diagnosis by transforming the latent space of black-box models into human-understandable concepts. However, concept-based methods still face challenges in concept capture capabilities. These methods often rely on encode features solely from the final layer, neglecting shallow and multiscale features, and lack effective guidance in concept encoding, hindering fine-grained concept extraction. To address these issues, we introduce Concept Prompting and Aggregating (CoPA), a novel framework designed to capture multilayer concepts under prompt guidance. This framework utilizes the Concept-aware Embedding Generator (CEG) to extract concept representations from each layer of the visual encoder. Simultaneously, these representations serve as prompts for Concept Prompt Tuning (CPT), steering the model towards amplifying critical concept-related visual cues. Visual representations from each layer are aggregated to align with textual concept representations. With the proposed method, valuable concept-wise information in the images is captured and utilized effectively, thus improving the performance of concept and disease prediction. Extensive experimental results demonstrate that CoPA outperforms state-of-the-art methods on three public datasets. Code is available at https://github.com/yihengd/CoPA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03767 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoPA: Hierarchical Concept Prompting and Aggregating Network for Explainable Diagnosis Dong, Yiheng Lin, Yi Yang, Xin Computer Vision and Pattern Recognition The transparency of deep learning models is essential for clinical diagnostics. Concept Bottleneck Model provides clear decision-making processes for diagnosis by transforming the latent space of black-box models into human-understandable concepts. However, concept-based methods still face challenges in concept capture capabilities. These methods often rely on encode features solely from the final layer, neglecting shallow and multiscale features, and lack effective guidance in concept encoding, hindering fine-grained concept extraction. To address these issues, we introduce Concept Prompting and Aggregating (CoPA), a novel framework designed to capture multilayer concepts under prompt guidance. This framework utilizes the Concept-aware Embedding Generator (CEG) to extract concept representations from each layer of the visual encoder. Simultaneously, these representations serve as prompts for Concept Prompt Tuning (CPT), steering the model towards amplifying critical concept-related visual cues. Visual representations from each layer are aggregated to align with textual concept representations. With the proposed method, valuable concept-wise information in the images is captured and utilized effectively, thus improving the performance of concept and disease prediction. Extensive experimental results demonstrate that CoPA outperforms state-of-the-art methods on three public datasets. Code is available at https://github.com/yihengd/CoPA. |
| title | CoPA: Hierarchical Concept Prompting and Aggregating Network for Explainable Diagnosis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.03767 |