Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations

• URL: http://arxiv.org/abs/2601.12303v1
• Date: Sun, 18 Jan 2026 08:01:44 GMT
• Title: Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations
• Authors: Shizhan Gong, Xiaofan Zhang, Qi Dou,
• Abstract summary: This paper introduces PCBM-ReD, a novel pipeline that retrofits interpretability onto pretrained opaque models.<n>It achieves state-of-the-art accuracy, narrows the performance gap with end-to-end models, and exhibits better interpretability.
• Score: 20.859723044900154
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning has achieved remarkable success in image recognition, yet their inherent opacity poses challenges for deployment in critical domains. Concept-based interpretations aim to address this by explaining model reasoning through human-understandable concepts. However, existing post-hoc methods and ante-hoc concept bottleneck models (CBMs), suffer from limitations such as unreliable concept relevance, non-visual or labor-intensive concept definitions, and model or data-agnostic assumptions. This paper introduces Post-hoc Concept Bottleneck Model via Representation Decomposition (PCBM-ReD), a novel pipeline that retrofits interpretability onto pretrained opaque models. PCBM-ReD automatically extracts visual concepts from a pre-trained encoder, employs multimodal large language models (MLLMs) to label and filter concepts based on visual identifiability and task relevance, and selects an independent subset via reconstruction-guided optimization. Leveraging CLIP's visual-text alignment, it decomposes image representations into linear combination of concept embeddings to fit into the CBMs abstraction. Extensive experiments across 11 image classification tasks show PCBM-ReD achieves state-of-the-art accuracy, narrows the performance gap with end-to-end models, and exhibits better interpretability.

Related papers

• Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs [51.378834857406325]
  Mechanistic interpretability seeks to mitigate the issues through extracts from large language models.<n>Sparse autoencoders (SAEs) have emerged as a popular approach for extracting interpretable and monosemantic concepts.<n>We show that SAEs suffer from a fundamental theoretical ambiguity: the well-defined correspondence between LLM representations and human-interpretable concepts remains unclear.
  arXiv  Detail & Related papers  (2026-01-28T09:27:05Z)
• GloTok: Global Perspective Tokenizer for Image Reconstruction and Generation [51.95701097588426]
  We introduce a Global Perspective Tokenizer (GloTok) to model a more uniform semantic distribution of tokenized features.<n>A residual learning module is proposed to recover the fine-grained details to minimize the reconstruction error caused by quantization.<n>Experiments on the standard ImageNet-1k benchmark clearly show that our proposed method achieves state-of-the-art reconstruction performance and generation quality.
  arXiv  Detail & Related papers  (2025-11-18T06:40:26Z)
• FaCT: Faithful Concept Traces for Explaining Neural Network Decisions [56.796533084868884]
  Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge.<n>We put emphasis on the faithfulness of concept-based explanations and propose a new model with model-inherent mechanistic concept-explanations.<n>Our concepts are shared across classes and, from any layer, their contribution to the logit and their input-visualization can be faithfully traced.
  arXiv  Detail & Related papers  (2025-10-29T13:35:46Z)
• Towards more holistic interpretability: A lightweight disentangled Concept Bottleneck Model [5.700536552863068]
  Concept Bottleneck Models (CBMs) enhance interpretability by predicting human-understandable concepts as intermediate representations.<n>We propose a lightweight Disentangled Concept Bottleneck Model (LDCBM) that automatically groups visual features into semantically meaningful components.<n> Experiments on three diverse datasets demonstrate that LDCBM achieves higher concept and class accuracy, outperforming previous CBMs in both interpretability and classification performance.
  arXiv  Detail & Related papers  (2025-10-17T15:59:30Z)
• Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts [79.18608192761512]
  Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable.<n>We propose a Few-Shot Prototypical Concept Classification framework that mitigates two key challenges under low-data regimes: parametric imbalance and representation misalignment.<n>Our approach consistently outperforms existing SEMs by a notable margin, with 4.2%-8.7% relative gains in 5-way 5-shot classification.
  arXiv  Detail & Related papers  (2025-06-05T06:39:43Z)
• Mod-Adapter: Tuning-Free and Versatile Multi-concept Personalization via Modulation Adapter [57.49476151976054]
  We propose a tuning-free method for multi-concept personalization that can effectively customize both object and abstract concepts without test-time fine-tuning.<n>Our method achieves state-of-the-art performance in multi-concept personalization, supported by quantitative, qualitative, and human evaluations.
  arXiv  Detail & Related papers  (2025-05-24T09:21:32Z)
• Concept Layers: Enhancing Interpretability and Intervenability via LLM Conceptualization [2.163881720692685]
  We introduce a new methodology for incorporating interpretability and intervenability into an existing model by integrating Concept Layers into its architecture.<n>Our approach projects the model's internal vector representations into a conceptual, explainable vector space before reconstructing and feeding them back into the model.<n>We evaluate CLs across multiple tasks, demonstrating that they maintain the original model's performance and agreement while enabling meaningful interventions.
  arXiv  Detail & Related papers  (2025-02-19T11:10:19Z)
• V2C-CBM: Building Concept Bottlenecks with Vision-to-Concept Tokenizer [19.177297480709512]
  Concept Bottleneck Models (CBMs) offer inherent interpretability by translating images into human-comprehensible concepts.<n>Recent approaches have leveraged the knowledge of large language models to construct concept bottlenecks.<n>In this study, we investigate to avoid these issues by constructing CBMs directly from multimodal models.
  arXiv  Detail & Related papers  (2025-01-09T05:12:38Z)
• DCBM: Data-Efficient Visual Concept Bottleneck Models [13.36057999450821]
  Concept Bottleneck Models (CBMs) enhance interpretability of neural networks by basing predictions on human-understandable concepts.<n>We propose Data-efficient CBMs, which reduce the need for large sample sizes during concept generation while preserving interpretability.
  arXiv  Detail & Related papers  (2024-12-16T09:04:58Z)
• Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models [57.86303579812877]
  Concept Bottleneck Models (CBMs) ground image classification on human-understandable concepts to allow for interpretable model decisions. Existing approaches often require numerous human interventions per image to achieve strong performances. We introduce a trainable concept realignment intervention module, which leverages concept relations to realign concept assignments post-intervention.
  arXiv  Detail & Related papers  (2024-05-02T17:59:01Z)
• Incremental Residual Concept Bottleneck Models [29.388549499546556]
  Concept Bottleneck Models (CBMs) map the black-box visual representations extracted by deep neural networks onto a set of interpretable concepts. We propose the Incremental Residual Concept Bottleneck Model (Res-CBM) to address the challenge of concept completeness. Our approach can be applied to any user-defined concept bank, as a post-hoc processing method to enhance the performance of any CBMs.
  arXiv  Detail & Related papers  (2024-04-13T12:02:19Z)
• Implicit Concept Removal of Diffusion Models [92.55152501707995]
  Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. We present the Geom-Erasing, a novel concept removal method based on the geometric-driven control.
  arXiv  Detail & Related papers  (2023-10-09T17:13:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.