The DOI matches its Crossref record; 106 of the 107 references it cites were found in a registry or an index.
Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals
Abstract
Being able to learn dense semantic representations of images without supervision is an important problem in computer vision. However, despite its significance, this problem remains rather unexplored, with a few exceptions that considered unsupervised semantic segmentation on small-scale datasets with a narrow visual domain. In this paper, we make a first attempt to tackle the problem on datasets that have been traditionally utilized for the supervised case. To achieve this, we introduce a two-step framework that adopts a predetermined mid-level prior in a contrastive optimization objective to learn pixel embeddings. This marks a large deviation from existing works that relied on proxy tasks or end-to-end clustering. Additionally, we argue about the importance of having a prior that contains information about objects, or their parts, and discuss several possibilities to obtain such a prior in an unsupervised manner.Experimental evaluation shows that our method comes with key advantages over existing works. First, the learned pixel embeddings can be directly clustered in semantic groups using K-Means on PASCAL. Under the fully unsupervised setting, there is no precedent in solving the semantic segmentation task on such a challenging benchmark. Second, our representations can improve over strong baselines when transferred to new datasets, e.g. COCO and DAVIS. The code is available1.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“2) Due to the lack of clear problem definition and standardized evaluation, some methods utilize supervised prior knowledge, e.g., supervised pre-trained network weights [46], supervised edge detection [30], and supervised saliency detection [31], [47], [48], making it difficult to evaluate these methods.”
From Large-Scale Unsupervised Semantic Segmentation (2023) · cites this paper as [31]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599
Normalized cuts and image segmentation
Shi, J., & Malik, J. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.868688 · Cited by 15,935
Momentum Contrast for Unsupervised Visual Representation Learning
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00975 · Cited by 13,347
The Cityscapes Dataset for Semantic Urban Scene Understanding
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.350 · Cited by 12,433
A simple framework for contrastive learning of visual representations
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020) · arXiv · doi:10.48550/arxiv.2002.05709 · Cited by 10,857
Multi-scale context aggregation by dilated convolutions
Yu, F., & Koltun, V. (2015) · arXiv · doi:10.48550/arxiv.1511.07122 · Cited by 7,738
Rethinking Atrous Convolution for Semantic Image Segmentation
Chen, L.-C., Papandreou, G., Schroff, F., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1706.05587 · Cited by 7,517
Research works printed but not linked: 3
- 10.1109/ICCV.2019.00996 · DOI
- ouali, 2020, Autore-gressive unsupervised image segmentation, ECCV
- bearman, 2016, What’s the point: Semantic segmentation with point supervision, ECCV
Cited by
Sorted by citations
Items 201–230 of 230
DMSA: Dynamic Multi-Scale Unsupervised Semantic Segmentation Based On Adaptive Affinity
Yang, K., & Lu, J. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096488
Self-Supervised Learning of Object Segmentation from Unlabeled RGB-D Videos
Lu, S., Deng, Y., Boularias, A., & Bekris, K. E. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160786
Ghosh, R., & Bovolo, F. (2023) · doi:10.36227/techrxiv.23987301
Adaptive Cluster Assignment for Unsupervised Semantic Segmentation
Shengqi, L., Liu, Q., Zhang, C., & Liang, Y. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8462-6_7
Global and Local Aware Learning Network for Semi-Supervised Cell Image SegmentationPreprint
Zhao, L., Yang, J., Li, K., Ding, W., Hu, B., & Zhou, H. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4681442
Enhancing Promotional Strategy Mapping Using the K-Means Clustering Algorithm to Raise Sales
Fathurrozi, A., & Laksana, T. G. (2024) · is The Best Accounting Information Systems and Information Technology Business Enterprise this is link for OJS us · doi:10.34010/aisthebest.v8i2.11597
S$^{{\text{3}}}$Seg: A Three-Stage Unsupervised Foreground and Background Segmentation Network
Yang, Z., Shen, Y., Hou, L., Zhang, W. E., & Chen, T. (2024) · IEEE Signal Processing Letters · doi:10.1109/lsp.2024.3404348
Semantic segmentation of street scenes under complex weather conditions
Liu, S., Jin, J., & Li, D. (2024) · International Conference on Electronic Information Engineering, Big Data and Computer Technology (EIBDCT) · doi:10.1117/12.3031346
Wang, L., Wang, L., Tang, L., Kuai, Z., Zhang, J., & Wei, H. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888102
Self-supervised Semantic Segmentation from Audio-Visual Data
Panagiotopoulos, A., Toh, M., Afouras, T., & Asano, Y. M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-85181-0_3
Dynaguide: A Generalizable Dynamic Guidance Framework for Unsupervised Semantic SegmentationPreprint
Guermazi, B., Ksantini, R., & Khan, N. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5273905
Unveiling Semantic Structure - Event-Driven Framework for Video Analysis
Deore, S. P., Machkar, T., Dontulwar, T., & Maheshwari, R. (2025) · OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry (OTCON) · doi:10.1109/otcon65728.2025.11070427
SegUnify: A Unified Framework for Unsupervised Semantic Segmentation
Prachi, Juneja, E., & Lalit, R. (2025) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom66777.2025.11115882
An Unsupervised Semantic Segmentation Model for Pulp Fibers in Paper Industries
Zhou, Y., & Liu, Y. (2025) · International Conference on Computer Science and Blockchain (CCSB) · doi:10.1109/ccsb66722.2025.11154166
Unsupervised Brain Tumor Segmentation via Bi-Level Optimization Guided by Radiological Reports
Zhang, P., Pang, H., Zhang, X., Gao, X., Liu, C., Hong, X., Jiang, R., Liu, Y., & Ye, C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05472-2_3
Component Adaptive Clustering for Generalized Category Discovery
Yan, M., Huang, J., Liu, Y., & Chen, S. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209408
AI-Based Automatic Prostate Gland Segmentation in Multi-modal Medical Imaging: A Review
Xu, D., Jin, R., Lu, F., Li, D., Xiang, D., Zhang, L., Zhou, H., Shi, F., Zhu, W., Cai, J., et al. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3640597
Zhu, L., Ren, S., Zhang, C., & Zhang, M. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05103-0
Localization knowledge-driven segmentation of arteries in ultrasound images
Yan, M., Wang, Z., Li, Z., Wang, P., Wu, P., Chen, X., Du, L., Li, L., Chang, H., & Fang, Z. (2026) · Displays · doi:10.1016/j.displa.2026.103381
Recent advances of local mechanisms in vision foundation models: A survey and outlook
Wang, Q., Li, J., Yin, Y., & Lu, H. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104679 · Cited by 1
Unsupervised object segmentation based on multi-background feature similarity
Luo, Q., Huang, T., Liu, F., & Wei, Z. (2025) · Asia Conference on Machine Learning and Computing (ACMLC) · doi:10.1145/3772673.3772705
Prototype-oriented contrastive mean-teacher for unsupervised domain adaptive object detection
Cao, Q., Tao, J., Dan, Y., & Zhou, D. (2026) · Scientific Reports · doi:10.1038/s41598-026-44991-7
Su, J., Luo, Q., Sun, S., Hou, Y., Zhang, X., Heikkilä, J., Yang, C., & Liu, L. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3673339
Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detection
Lu, Y., Nie, S., Lu, M., Yang, X., Zhang, X., & Zhang, P. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01789
RCPR: Robust Consensus Prototype Refinement for Self-Supervised Co-Salient Object Detection
Xu, Y., & Chen, K. (2026) · International Conference on Artificial Intelligence and Advanced Autonomous Systems · doi:10.1145/3813723.3813741
Ma, Z., Li, Y., Ma, R., & Liang, C. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-3548-3_2
A Fully Unsupervised Framework for Object Mask Labeling with the Self-supervised Vision Transformer
Kumar, S., Jitendrabhai, K. S., Daydar, A., Sur, A., & Baruah, R. D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31920-3_8
Post-MI: unsupervised brain tissue segmentation via post-maximized mutual information
Niu, K., Guo, J., Zhang, M., Guo, Z., Cai, J., Xiao, N., Jiang, B., & Miao, H. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2026.1852159
RGB-D Salient Object Detection: A SurveyPreprint
Xiao, H., Li, J., Xiang, Y., Zhou, F., Liu, X., Yang, Z., & Tao, A. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7385363
Label-Free Semantic Segmentation via Soft Superpixel-Graph Coupling
Eliasof, M., Zikri, N. B., & Treister, E. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37657-2_37
Metadata
- Authors
- Van Gansbeke, W., Vandenhende, S., Georgoulis, S., & Van Gool, L.
- Affiliations
- KU Leuven/ESAT-PSI
- KU Leuven (BE)
- ETH Zurich (CH)
- Venue
- 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2021-10
- Pages
- 10032-10042
- OpenAlex
- W3129110783
- Cited by
- 231
- References
- 107
- Citations by year
- 2026: 12 · 2025: 34 · 2024: 57 · 2023: 69 · 2022: 45 · 2021: 14
- FWCI
- 15.04
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- Funders
- KU Leuven
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Keywords
- unsupervised semantic segmentation, contrastive learning, pixel embedding, semantic clustering, domain transfer, COCO, Davis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
