Unsupervised Image Segmentation

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 11

All topics

Seeing as Humans Do: Learning from Motion to Segment Anything Without Supervision
Sep 30, 2026Weijian Jian, Xiaoyue Zhang, Bin Xiao +5Image Segmentation Self-Supervised Learning
AI Research · Independent Researcher · University of Ottawa +1
ProGuT: Label-Efficient Panoptic Segmentation for Forest Scenes
Sep 29, 2026Pankaj Deoli, Karsten BernsImage Segmentation Panoptic Segmentation
Robotics Research Lab, RPTU Kaiserslautern-Landau Gottlieb-Daimler-Str. 48, 67663 Kaiserslautern, Germany
Can Frozen Hyperspherical Features Guide the Selection of Pseudo Masks?
Sep 24, 2026Xinge Guo, Fengyang Xiao, Dingming Zhang +6Promptable Image Segmentation Pseudo-Labeling
Duke University · Carnegie Mellon University · University of Alabama at Birmingham
ICM: Intra-class Mixing for Domain Adaptation in Adverse Weather
Sep 23, 2026Boying Li, Chang Liu, Britta Ayano Wilde +4Unsupervised Domain Adaptation Domain Adaptation
PixelUp: Zero-Shot Semantic Feature Upsampling for Fine-Grained Vision Tasks
Aug 3, 2026Deepank Singh, Anurag Nihal, Vedhus HoskereDepth Estimation Vision Foundation Model Adaptation
University of Houston
UMSS: Towards Unsupervised Multi-modal Semantic Segmentation
Jul 14, 2026Haitian Zhang, Thai Duy Nguyen, Xiangyuan Wang +2Cross-Modal Representation Learning Semantic Segmentation
EmPACT Lab, School of EEE, Nanyang Technological University, Singapore · The University of Hong Kong, Hong Kong SAR, China
Speeding up the annotation process in semantic segmentation industrial applications
Jun 18, 2026Marta Fernandez-Moreno, Margarita Guerrero, Rosalia Rementeria +2Human-in-the-Loop Annotation Semantic 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
Unsupervised Semantic Segmentation Facilitates Model Understanding
May 28, 2026Xiaoyan Yu, Lisa Mais, Jannik Franzen +4Transformer Interpretability Vision Transformer
Max-Delbrück-Center (MDC), Berlin, Germany · Helmholtz Imaging · Humboldt-Universität zu Berlin, Berlin, Germany +2
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 Segmentation Medical 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
Deep Sprite-based Image Models: An Analysis
Apr 21, 2026Zeynep Sonat Baltacı, Romain Loiseau, Mathieu AubryClustering Object-Centric Representation Learning
LIGM, CNRS, Univ Gustave Eiffel, ENPC, Institut Polytechnique de Paris, France
Segmenting Low-Contrast XCTs of Concrete: An Unsupervised Approach
Feb 23, 2026Kaustav Das, Gaston Rauchs, Jan Sykora +1Image Segmentation Computed Tomography
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

Sep 30, 2026, cs.CVJ/K move · Enter open · S save

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

Weijian Jian, Xiaoyue Zhang, Bin Xiao, Chunyu Xie+4

AI Research · Independent Researcher · University of Ottawa+1

Image Segmentation Self-Supervised Learning Promptable Image Segmentation Unsupervised Image Segmentation

Open paper AskPDF arXiv

The Segment Anything Model (SAM) relies heavily on massive manual annotations, creating a fundamental bottleneck for model scaling. While unsupervised methods attempt to learn object concepts from motion, they typically overfit to moving entities, lacking both multi-granularity understanding and the ability to generalize to static objects. To overcome this, we introduce Motion-Grounded Segment Anything (MoSA), a highly scalable unsupervised framework that learns a transferable objectness prior from unlabeled videos. MoSA operates in three progressive stages: (1) automatically generating multi-granularity motion pseudo-labels from large-scale video data; (2) training a Perceptual Grouping Model (PGM) via contrastive learning to internalize a generalized, appearance-driven concept of objects; and (3) transferring this learned prior into a prompt-guided architecture for segment-anything-style inference on images. Extensive zero-shot evaluations across seven challenging benchmarks (e.g., COCO and ADE20K) demonstrate that MoSA significantly outperforms existing unsupervised methods. Notably, despite using zero manual annotations, MoSA achieves segmentation performance comparable to the fully supervised SAM. Our findings reveal that harnessing large-scale unlabeled motion is a feasible and highly scalable alternative to annotation-driven segment-anything pipelines.

Momentum

Related topics

Latest papers 11