Language Guided Concept Bottleneck Models for Interpretable Continual Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yu, Lu, Han, Haoyu, Tao, Zhe, Yao, Hantao, Xu, Changsheng
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909557859549184
author Yu, Lu
Han, Haoyu
Tao, Zhe
Yao, Hantao
Xu, Changsheng
author_facet Yu, Lu
Han, Haoyu
Tao, Zhe
Yao, Hantao
Xu, Changsheng
contents Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating catastrophic forgetting while maintaining interpretability across tasks. Most existing CL methods focus primarily on preserving learned knowledge to improve model performance. However, as new information is introduced, the interpretability of the learning process becomes crucial for understanding the evolving decision-making process, yet it is rarely explored. In this paper, we introduce a novel framework that integrates language-guided Concept Bottleneck Models (CBMs) to address both challenges. Our approach leverages the Concept Bottleneck Layer, aligning semantic consistency with CLIP models to learn human-understandable concepts that can generalize across tasks. By focusing on interpretable concepts, our method not only enhances the models ability to retain knowledge over time but also provides transparent decision-making insights. We demonstrate the effectiveness of our approach by achieving superior performance on several datasets, outperforming state-of-the-art methods with an improvement of up to 3.06% in final average accuracy on ImageNet-subset. Additionally, we offer concept visualizations for model predictions, further advancing the understanding of interpretable continual learning.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23283
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Language Guided Concept Bottleneck Models for Interpretable Continual Learning
Yu, Lu
Han, Haoyu
Tao, Zhe
Yao, Hantao
Xu, Changsheng
Computer Vision and Pattern Recognition
Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating catastrophic forgetting while maintaining interpretability across tasks. Most existing CL methods focus primarily on preserving learned knowledge to improve model performance. However, as new information is introduced, the interpretability of the learning process becomes crucial for understanding the evolving decision-making process, yet it is rarely explored. In this paper, we introduce a novel framework that integrates language-guided Concept Bottleneck Models (CBMs) to address both challenges. Our approach leverages the Concept Bottleneck Layer, aligning semantic consistency with CLIP models to learn human-understandable concepts that can generalize across tasks. By focusing on interpretable concepts, our method not only enhances the models ability to retain knowledge over time but also provides transparent decision-making insights. We demonstrate the effectiveness of our approach by achieving superior performance on several datasets, outperforming state-of-the-art methods with an improvement of up to 3.06% in final average accuracy on ImageNet-subset. Additionally, we offer concept visualizations for model predictions, further advancing the understanding of interpretable continual learning.
title Language Guided Concept Bottleneck Models for Interpretable Continual Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.23283