Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations

• URL: http://arxiv.org/abs/2508.01728v1
• Date: Sun, 03 Aug 2025 11:45:38 GMT
• Title: Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations
• Authors: Dahee Kwon, Sehyun Lee, Jaesik Choi,
• Abstract summary: We introduce an effective circuit discovery method, called Granular Concept Circuit (GCC), in which each circuit represents a concept relevant to a given query.<n>By automatically discovering multiple circuits, each capturing specific concepts within that query, our approach offers a profound, concept-wise interpretation of models.<n>We validate the versatility and effectiveness of GCCs across various deep image classification models.
• Score: 19.50321703079894
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep vision models have achieved remarkable classification performance by leveraging a hierarchical architecture in which human-interpretable concepts emerge through the composition of individual neurons across layers. Given the distributed nature of representations, pinpointing where specific visual concepts are encoded within a model remains a crucial yet challenging task. In this paper, we introduce an effective circuit discovery method, called Granular Concept Circuit (GCC), in which each circuit represents a concept relevant to a given query. To construct each circuit, our method iteratively assesses inter-neuron connectivity, focusing on both functional dependencies and semantic alignment. By automatically discovering multiple circuits, each capturing specific concepts within that query, our approach offers a profound, concept-wise interpretation of models and is the first to identify circuits tied to specific visual concepts at a fine-grained level. We validate the versatility and effectiveness of GCCs across various deep image classification models.

Related papers

• Discovering Concept Directions from Diffusion-based Counterfactuals via Latent Clustering [4.891597567642704]
  Concept-based explanations have emerged as an effective approach within Explainable Artificial Intelligence.<n>This work introduces Concept Directions via Latent Clustering (CDLC), which extracts global, class-specific concept directions.<n>This approach is validated on a real-world skin lesion dataset.
  arXiv  Detail & Related papers  (2025-05-11T17:53:02Z)
• OmniPrism: Learning Disentangled Visual Concept for Image Generation [57.21097864811521]
  Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes.<n>We propose OmniPrism, a visual concept disentangling approach for creative image generation.<n>Our method learns disentangled concept representations guided by natural language and trains a diffusion model to incorporate these concepts.
  arXiv  Detail & Related papers  (2024-12-16T18:59:52Z)
• Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery [52.498055901649025]
  Concept Bottleneck Models (CBMs) have been proposed to address the 'black-box' problem of deep neural networks. We propose a novel CBM approach -- called Discover-then-Name-CBM (DN-CBM) -- that inverts the typical paradigm. Our concept extraction strategy is efficient, since it is agnostic to the downstream task, and uses concepts already known to the model.
  arXiv  Detail & Related papers  (2024-07-19T17:50:11Z)
• Automatic Discovery of Visual Circuits [66.99553804855931]
  We explore scalable methods for extracting the subgraph of a vision model's computational graph that underlies recognition of a specific visual concept. We find that our approach extracts circuits that causally affect model output, and that editing these circuits can defend large pretrained models from adversarial attacks.
  arXiv  Detail & Related papers  (2024-04-22T17:00:57Z)
• Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models [21.245185285617698]
  Visual Concept Connectome (VCC) discovers human interpretable concepts and their interlayer connections in a fully unsupervised manner. Our approach simultaneously reveals fine-grained concepts at a layer, connection weightings across all layers and is amendable to global analysis of network structure.
  arXiv  Detail & Related papers  (2024-04-02T18:40:55Z)
• Coarse-to-Fine Concept Bottleneck Models [9.910980079138206]
  This work targets ante hoc interpretability, and specifically Concept Bottleneck Models (CBMs) Our goal is to design a framework that admits a highly interpretable decision making process with respect to human understandable concepts, on two levels of granularity. Within this framework, concept information does not solely rely on the similarity between the whole image and general unstructured concepts; instead, we introduce the notion of concept hierarchy to uncover and exploit more granular concept information residing in patch-specific regions of the image scene.
  arXiv  Detail & Related papers  (2023-10-03T14:57:31Z)
• ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation [17.019848796027485]
  Self-supervised visual pre-training models have shown great promise in representing pixel-level semantic relationships. In this work, we investigate the pixel-level semantic aggregation in self-trained models as image encodes and design concepts. We propose the Adaptive Concept Generator (ACG) which adaptively maps these prototypes to informative concepts for each image.
  arXiv  Detail & Related papers  (2022-10-12T06:16:34Z)
• Automatic Concept Extraction for Concept Bottleneck-based Video Classification [58.11884357803544]
  We present an automatic Concept Discovery and Extraction module that rigorously composes a necessary and sufficient set of concept abstractions for concept-based video classification. Our method elicits inherent complex concept abstractions in natural language to generalize concept-bottleneck methods to complex tasks.
  arXiv  Detail & Related papers  (2022-06-21T06:22:35Z)
• SegDiscover: Visual Concept Discovery via Unsupervised Semantic Segmentation [29.809900593362844]
  SegDiscover is a novel framework that discovers semantically meaningful visual concepts from imagery datasets with complex scenes without supervision. Our method generates concept primitives from raw images, discovering concepts by clustering in the latent space of a self-supervised pretrained encoder, and concept refinement via neural network smoothing.
  arXiv  Detail & Related papers  (2022-04-22T20:44:42Z)
• Interpretable Visual Reasoning via Induced Symbolic Space [75.95241948390472]
  We study the problem of concept induction in visual reasoning, i.e., identifying concepts and their hierarchical relationships from question-answer pairs associated with images. We first design a new framework named object-centric compositional attention model (OCCAM) to perform the visual reasoning task with object-level visual features. We then come up with a method to induce concepts of objects and relations using clues from the attention patterns between objects' visual features and question words.
  arXiv  Detail & Related papers  (2020-11-23T18:21:49Z)
• Visual Concept Reasoning Networks [93.99840807973546]
  A split-transform-merge strategy has been broadly used as an architectural constraint in convolutional neural networks for visual recognition tasks. We propose to exploit this strategy and combine it with our Visual Concept Reasoning Networks (VCRNet) to enable reasoning between high-level visual concepts. Our proposed model, VCRNet, consistently improves the performance by increasing the number of parameters by less than 1%.
  arXiv  Detail & Related papers  (2020-08-26T20:02:40Z)

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.