# Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models

Source: [Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models](<https://www.sota2.com/research/paper/68fa72e11e209131cea59230>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:36:44.860Z

Authors: Matthew Kowal, Richard P. Wildes, Konstantinos G. Derpanis

Published: 2024-04-02T18:40:55.000Z

## Abstract

Understanding what deep network models capture in their learned representations is a fundamental challenge in computer vision. We present a new methodology to understanding such vision models, the Visual Concept Connectome (VCC), which 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 (e.g., branching pattern of hierarchical concept assemblies). Previous work yielded ways to extract interpretable concepts from single layers and examine their impact on classification, but did not afford multilayer concept analysis across an entire network architecture. Quantitative and qualitative empirical results show the effectiveness of VCCs in the domain of image classification. Also, we leverage VCCs for the application of failure mode debugging to reveal where mistakes arise in deep networks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2404.02233>)

[PDF](<https://arxiv.org/pdf/2404.02233.pdf>)