AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate Diagnosis

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chowdhury, Townim F., Phan, Vu Minh Hieu, Liao, Kewen, To, Minh-Son, Xie, Yutong, Hengel, Anton van den, Verjans, Johan W., Liao, Zhibin
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929449414426624
author Chowdhury, Townim F.
Phan, Vu Minh Hieu
Liao, Kewen
To, Minh-Son
Xie, Yutong
Hengel, Anton van den
Verjans, Johan W.
Liao, Zhibin
author_facet Chowdhury, Townim F.
Phan, Vu Minh Hieu
Liao, Kewen
To, Minh-Son
Xie, Yutong
Hengel, Anton van den
Verjans, Johan W.
Liao, Zhibin
contents The integration of vision-language models such as CLIP and Concept Bottleneck Models (CBMs) offers a promising approach to explaining deep neural network (DNN) decisions using concepts understandable by humans, addressing the black-box concern of DNNs. While CLIP provides both explainability and zero-shot classification capability, its pre-training on generic image and text data may limit its classification accuracy and applicability to medical image diagnostic tasks, creating a transfer learning problem. To maintain explainability and address transfer learning needs, CBM methods commonly design post-processing modules after the bottleneck module. However, this way has been ineffective. This paper takes an unconventional approach by re-examining the CBM framework through the lens of its geometrical representation as a simple linear classification system. The analysis uncovers that post-CBM fine-tuning modules merely rescale and shift the classification outcome of the system, failing to fully leverage the system's learning potential. We introduce an adaptive module strategically positioned between CLIP and CBM to bridge the gap between source and downstream domains. This simple yet effective approach enhances classification performance while preserving the explainability afforded by the framework. Our work offers a comprehensive solution that encompasses the entire process, from concept discovery to model training, providing a holistic recipe for leveraging the strengths of GPT, CLIP, and CBM.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02001
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate Diagnosis
Chowdhury, Townim F.
Phan, Vu Minh Hieu
Liao, Kewen
To, Minh-Son
Xie, Yutong
Hengel, Anton van den
Verjans, Johan W.
Liao, Zhibin
Computer Vision and Pattern Recognition
The integration of vision-language models such as CLIP and Concept Bottleneck Models (CBMs) offers a promising approach to explaining deep neural network (DNN) decisions using concepts understandable by humans, addressing the black-box concern of DNNs. While CLIP provides both explainability and zero-shot classification capability, its pre-training on generic image and text data may limit its classification accuracy and applicability to medical image diagnostic tasks, creating a transfer learning problem. To maintain explainability and address transfer learning needs, CBM methods commonly design post-processing modules after the bottleneck module. However, this way has been ineffective. This paper takes an unconventional approach by re-examining the CBM framework through the lens of its geometrical representation as a simple linear classification system. The analysis uncovers that post-CBM fine-tuning modules merely rescale and shift the classification outcome of the system, failing to fully leverage the system's learning potential. We introduce an adaptive module strategically positioned between CLIP and CBM to bridge the gap between source and downstream domains. This simple yet effective approach enhances classification performance while preserving the explainability afforded by the framework. Our work offers a comprehensive solution that encompasses the entire process, from concept discovery to model training, providing a holistic recipe for leveraging the strengths of GPT, CLIP, and CBM.
title AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate Diagnosis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.02001