Unsupervised Image Segmentation

Ask about this topic

Overview

Unsupervised image segmentation seeks pixel-level groups and object boundaries from unlabeled images or videos, reducing the cost of annotation in settings such as natural scenes, medical imaging, and industrial inspection. Common approaches cluster self-supervised or foundation-model features, learn object-centric slots, exploit motion or diffusion-model representations, and refine automatically generated pseudo-labels; classical thresholding and filtering remain useful in specialized domains. Methods are increasingly able to produce semantic, instance, and multi-granularity masks, sometimes by adapting pretrained models without additional labels. A central challenge is turning coarse or noisy cues into reliable fine boundaries and consistent object identities across domains, while comparing results fairly when methods use different forms of pretrained data or supervision.

Latest papers

CardsList

23 papers6 papers in the last four weeks, up 100% on the four weeks before. 0.0% of all new papers.

  1. Complementing DINO Features with Image Structure for Part Discovery

    Oct 23, 2026Samyak Rawlekar, Nikhil Chowdary Paleti, Amey Gupta +1Unsupervised Image Segmentation

    University of Illinois Urbana-Champaign Urbana, IL 61801 · Independent Researcher Sunnyvale, CA, 94087

  2. From Proper Scoring Rules and Edge Biases to Mumford-Shah Models: Robust Unsupervised Hyperspectral Image Segmentation

    Oct 20, 2026Fabian Conrad, Benjamin BerkelsRobust StatisticsRemote Sensing Image Segmentation

    IGPM, RWTH Aachen University, Germany

  3. FPG-Seg: Annotation-free Retinal Vessel Topology Segmentation

    Oct 15, 2026James Willoughby, Irina VoiculescuRetinal Vessel SegmentationUnsupervised Image Segmentation

    University of Oxford, Department of Computer Science

  4. Understanding Clustering in Slot Attention via Particle Dynamics

    Oct 3, 2026Vasudev Joy, Rajat Rasal, Avinash Kori +2Slot AttentionObject-Centric Representation Learning

    Imperial College London

  5. Seeing as Humans Do: Learning from Motion to Segment Anything Without Supervision

    Sep 30, 2026Weijian Jian, Xiaoyue Zhang, Bin Xiao +5Image SegmentationSelf-Supervised Learning

    AI Research · Independent Researcher · University of Ottawa +1

  6. ProGuT: Label-Efficient Panoptic Segmentation for Forest Scenes

    Sep 29, 2026Pankaj Deoli, Karsten BernsImage SegmentationPanoptic Segmentation

    Robotics Research Lab, RPTU Kaiserslautern-Landau Gottlieb-Daimler-Str. 48, 67663 Kaiserslautern, Germany

  7. Can Frozen Hyperspherical Features Guide the Selection of Pseudo Masks?

    Sep 24, 2026Xinge Guo, Fengyang Xiao, Dingming Zhang +6Promptable Image SegmentationPseudo-Labeling

    Duke University · Carnegie Mellon University · University of Alabama at Birmingham

  8. ICM: Intra-class Mixing for Domain Adaptation in Adverse Weather

    Sep 23, 2026Boying Li, Chang Liu, Britta Ayano Wilde +4Unsupervised Domain AdaptationDomain Adaptation

  9. Diffuse2Seg: Diffusion Models Can Segment Anything Without Supervision

    Sep 6, 2026Christoph Hümmer, Joachim Sicking, Fabian Hüger +1Unsupervised Image SegmentationInstance Segmentation

    Institute of Mathematics, Technical University of Berlin · CARIAD SE, Volkswagen Group

  10. Unsupervised Learning of Cell Instances with Generative Routing Pyramids

    Aug 17, 2026Ziwen Liu, Martin WeigertInstance SegmentationUnsupervised Image Segmentation

    Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI), Technische Universität Dresden, Germany

  11. PixelUp: Zero-Shot Semantic Feature Upsampling for Fine-Grained Vision Tasks

    Aug 3, 2026Deepank Singh, Anurag Nihal, Vedhus HoskereDepth EstimationVision Foundation Model Adaptation

    University of Houston

  12. UMSS: Towards Unsupervised Multi-modal Semantic Segmentation

    Jul 14, 2026Haitian Zhang, Thai Duy Nguyen, Xiangyuan Wang +2Cross-Modal Representation LearningMultimodal Semantic Segmentation

    EmPACT Lab, School of EEE, Nanyang Technological University, Singapore · The University of Hong Kong, Hong Kong SAR, China

  13. Speeding up the annotation process in semantic segmentation industrial applications

    Jun 18, 2026Marta Fernandez-Moreno, Margarita Guerrero, Rosalia Rementeria +2Human-in-the-Loop AnnotationSemantic Segmentation

    Department of Computer Science and Artificial Intelligence, Andalusian Research Institute in Data Science and Computational Intelligence, DaSCI, University of Granada, 18071, Granada, Spain · Ingénica STS, Av. Pablo Iglesias 38, Bj, 33205, Gijón, Spain · ArcelorMittal Global R&D, SLab—Steel Labs, Calle Marineros 4, 33490, Avilés, Spain +1

  14. Unsupervised Semantic Segmentation Facilitates Model Understanding

    May 28, 2026Xiaoyan Yu, Lisa Mais, Jannik Franzen +4Transformer InterpretabilityVision Transformer

    Max-Delbrück-Center (MDC), Berlin, Germany · Helmholtz Imaging · Humboldt-Universität zu Berlin, Berlin, Germany +2

  15. Local-sensitive connectivity filter (ls-cf): A post-processing unsupervised improvement of the frangi, hessian and vesselness filters for multimodal vessel segmentation

    May 20, 2026Erick O Rodrigues, Lucas O Rodrigues, João HP Machado +5Retinal Vessel SegmentationMedical Image Segmentation

    Department of Academic Informatics (DAINF), Universidade Tecnologica Federal do Parana (UTFPR), Pato Branco 85503-390, PR, Brazil · Graduate Program of Sciences Applied to Health Products, Universidade Federal Fluminense (UFF), Niteroi 24241000, RJ, Brazil · Institute of Technological Sciences (ICT), Universidade Federal de Itajuba (UNIFEI), Ttabira 35903-087, MG, Brazil +1

  16. Deep Sprite-based Image Models: An Analysis

    Apr 21, 2026Zeynep Sonat Baltacı, Romain Loiseau, Mathieu AubryClusteringObject-Centric Representation Learning

    LIGM, CNRS, Univ Gustave Eiffel, ENPC, Institut Polytechnique de Paris, France

  17. Excite, Attend and Segment (EASe): Domain-Agnostic Fine-Grained Mask Discovery with Feature Calibration and Self-Supervised Upsampling

    Mar 31, 2026Deepank Singh, Anurag Nihal, Vedhus HoskereFine-Grained Semantic SegmentationImage Segmentation

    University of Houston, Houston, TX, USA

  18. When Slots Compete: Slot Merging in Object-Centric Learning

    Mar 11, 2026Christos Chatzisavvas, Panagiotis Rigas, George Ioannakis +2Object-Centric Representation LearningSlot Attention

    Department of Electrical and Computer Engineering, Democritus University of Thrace, Greece · Institute for Language and Speech Processing, Athena Research Center, Greece · Department of Informatics & Telecommunications, National and Kapodistrian University of Athens, Greece +1

  19. Unsupervised Semantic Segmentation in Synchrotron Computed Tomography with Self-Correcting Pseudo Labels

    Feb 27, 2026Austin Yunker, Peter Kenesei, Hemant Sharma +3Unsupervised Image Segmentation3D Semantic Segmentation

    Data Science and Learning Division, Argonne National Laboratory, Lemont, IL USA · X-Ray Science Division, Argonne National Laboratory, Lemont, IL USA

  20. Learning Accurate Segmentation Purely from Self-Supervision

    Feb 27, 2026Zuyao You, Zuxuan Wu, Yu-Gang JiangUnsupervised Image SegmentationSalient Object Detection

    Fudan University

  21. Segmenting Low-Contrast XCTs of Concrete: An Unsupervised Approach

    Feb 23, 2026Kaustav Das, Gaston Rauchs, Jan Sykora +1Image SegmentationSuperpixel Segmentation

    Department of Mechanics, Faculty of Civil Engineering, Czech Technical University in Prague, Thákurova 7, 166 29 Prague 6, Czech Republic · Structural Composites Unit, Luxembourg Institute of Science and Technology (LIST), 5 avenue des Hauts-Fourneaux L-4362 Esch-sur-Alzette, Luxembourg

  22. UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity

    Nov 17, 2025Junwei Yu, Trevor Darrell, XuDong WangImage SegmentationPromptable Image Segmentation

    UC Berkeley

  23. Multiclass histogram-based thresholding using kernel density estimation and scale-space representations

    Feb 10, 2022S. Korneev, J. Gilles, I. BattiatoUnsupervised Image SegmentationImage Segmentation