Unsupervised Visual Concept Discovery

Latest papers

13 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

DisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Models
Oct 7, 2026Adam Pardyl, Siddhartha Gairola, Sukrut Rao +4Unsupervised Visual Concept Discovery Explainable Image Classification
Jagiellonian University, Faculty of Mathematics and Computer Science · Jagiellonian University, Doctoral School of Exact and Natural Sciences · Max Planck Institute for Informatics, Saarland Informatics Campus +2
SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations
Sep 30, 2026Shuang Liang, Lejun Liao, Shiyuan Zhang +5Disentangled Representation Learning Conditional Image Generation
HKU · Boston College · University of Virginia +1
Real-time Unsupervised Object Discovery from Asynchronous Event Streams
Aug 27, 2026Pratham G. Shenwai, Hemant Kumar Singh, Sridhar RaviUnsupervised Visual Concept Discovery Event-Based Vision
School of Engineering and Technology University of New South Wales Canberra, Australia
Beyond Heatmaps: Unsupervised Concept-Graph Reasoning for Interpretable Visual Explanation
Jul 1, 2026Md Mohasin Hossain, Anar Amirli, Robert Leist +2Concept Bottleneck Models Concept-Based Explanations
German Research Center for Artificial Intelligence · Saarland University, Saarbrücken, Germany · BEGO GmbH & Co. KG, Bremen, Germany +1
Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?
Jun 22, 2026Nils Grandien, David Steinmann, Felix Friedrich +1Hierarchical Representation Learning Sparse Autoencoders
Computer Science Department, TU Darmstadt · Hessian Center for AI (hessian.AI) · Black Forest Labs +1
S $^2$ COPE: Self-Supervised Concept Discovery via Preference Learning
Jun 12, 2026Shilong Xiang, Zirui Zhang, Chengzhi MaoVision-Language Models Self-Supervised Learning
Rutgers University
MedConcept: Unsupervised Concept Discovery for Interpretability in Medical VLMs
Apr 13, 2026Md Rakibul Haque, KM Arefeen Sultan, Tushar Kataria +1Unsupervised Visual Concept Discovery VLM Interpretability
Kahlert School of Computing, University of Utah · Scientific Computing and Imaging Institute, University of Utah
Finding Distributed Object-Centric Properties in Self-Supervised Transformers
Mar 27, 2026Samyak Rawlekar, Amitabh Swain, Yujun Cai +3Unsupervised Visual Concept Discovery Vision Transformer
University of Illinois Urbana-Champaign · University of Queensland · UC Merced
From Topic to Transition Structure: Unsupervised Concept Discovery at Corpus Scale via Predictive Associative Memory
Mar 19, 2026Jason DuryUnsupervised Visual Concept Discovery Text Clustering
Independent Researcher
Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video
Mar 14, 2026Yuting Tan, Xilong Cheng, Yunxiao Qin +2Unsupervised Visual Concept Discovery Self-Supervised Visual Representation Learning
Communication University of China, Beijing, China · State Key Laboratory of Media Convergence and Communication, Beijing, China · The Chinese University of Hong Kong, Shenzhen
Unlocking ImageNet's Multi-Object Nature: Automated Large-Scale Multilabel Annotation
Mar 5, 2026Junyu Chen, Md Yousuf Harun, Christopher KananUnsupervised Visual Concept Discovery Multi-Label Classification
University of Rochester · Rochester Institute of Technology
ORGAN: Object-Centric Representation Learning using Cycle Consistent Generative Adversarial Networks
Mar 2, 2026Joël Küchler, Ellen van Maren, Vaiva Vasiliauskaitė +3Unsupervised Visual Concept Discovery Object-Centric Representation Learning
Laboratory of Biosensors and Bioelectronics, Institute for Biomedical Engineering, University and ETH Zurich, Gloriastrasse 37/39, Zurich, 8092, Switzerland · Department of Neurology, Insel Gruppe, Bern, Switzerland · Department of Neurology, Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, USA +2
Towards Open-Ended Visual Scientific Discovery with Sparse Autoencoders
Nov 21, 2025Jacob Beattie, Samuel Stevens, Neil Rosser +2Vision Foundation Models Sparse Autoencoders
The Ohio State University · The University of Miami

Oct 7, 2026J/K move · Enter open · S save

DisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Models

Adam Pardyl, Siddhartha Gairola, Sukrut Rao, Adam Wróbel+3

Jagiellonian University, Faculty of Mathematics and Computer Science · Jagiellonian University, Doctoral School of Exact and Natural Sciences · Max Planck Institute for Informatics, Saarland Informatics Campus+2

Unsupervised Visual Concept Discovery Explainable Image Classification Vision Foundation Models Self-Supervised Visual Representation Learning

Open paper AskPDF arXiv

Concept-based vision models represent images through an intermediate layer of human-inspectable concepts, so what a model relies on can be traced to those concepts. However, those models are often limited to fixed categories or depend on language to define their concepts. We introduce DisParQ (Discrete Parts with Quantized attributes), a method that learns spatially grounded, discrete concept representations from a powerful frozen vision-only self-supervised backbone. It requires no class labels and no language supervision. Each image patch is assigned to exactly one concept from a learnable prototype dictionary, and only a sparse subset of concepts may activate per image. To capture how each concept varies across images (e.g., the type of a "wheel"), we learn continuous residuals alongside the concepts and then quantize them into discrete attributes. A spatial decoder reconstructs the backbone's representation from the concepts and attributes alone, so successful reconstruction means that the discrete representation preserves the backbone's information. We evaluate DisParQ across seven datasets, from general recognition (ImageNet, PartImageNet, Places) to fine-grained benchmarks (CUB, Cars, Dogs, Flowers). We show that DisParQ closely matches its frozen DINOv2 teacher on ImageNet linear probing (83.2% top-1), achieves higher concept consistency than language-aligned models, remains competitive on fine-grained recognition, and enables cross-category part-based retrieval.