Hybrid Concept Bottleneck Models

Abstract

Concept Bottleneck Models (CBMs) provide an interpretable framework for neural networks by mapping visual features to predefined, human-understandable concepts. However, the application of CBMs is often constrained by insufficient concept annotations. Recently, multi-modal pre-trained models have shown promise in reducing annotation costs by aligning visual representations with textual concept embeddings. Nevertheless, the quality and completeness of the predefined concepts significantly affect the performance of CBMs. In this work, we propose Hybrid Concept Bottleneck Model (HybridCBM), a novel CBM framework to address the challenge of incomplete predefined concepts. Our method consists of two main components: a Static Concept Bank and a Dynamic Concept Bank. The Static Concept Bank directly leverages large language models (LLMs) for concept construction, while the Dynamic Concept Bank employs learnable vectors to capture complementary and valuable concepts continuously during training. After training, a pre-trained translator converts these vectors into human-understandable concepts, further enhancing model interpretability. HybridCBM is highly flexible and can be easily integrated with existing CBMs to improve both inter-pretability and performance. Experimental results1 on multiple datasets demonstrate that HybridCBM outperforms current state-of-the-art CBMs and achieves comparable results to black-box models. Additionally, we propose novel metrics to assess the quality of learned concepts, showing that they perform comparably to predefined concepts.