Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization
Open accessThe DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.
Abstract
Unsupervised localization and segmentation are long-standing computer vision challenges that involve decom-posing an image into semantically meaningful segments without any labeled data. These tasks are particularly interesting in an unsupervised setting due to the difficulty and cost of obtaining dense image annotations, but existing un-supervised approaches struggle with complex scenes containing multiple objects. Differently from existing methods, which are purely based on deep learning, we take inspiration from traditional spectral segmentation methods by re-framing image decomposition as a graph partitioning problem. Specifically, we examine the eigenvectors of the Laplacian of a feature affinity matrix from self-supervised networks. We find that these eigenvectors already decompose an image into meaningful segments, and can be readily used to localize objects in a scene. Furthermore, by clustering the features associated with these segments across a dataset, we can obtain well-delineated, nameable regions, i.e. semantic segmentations. Experiments on complex datasets (PASCAL VOC, MS-COCO) demonstrate that our simple spectral method outperforms the state-of-the-art in unsupervised localization and segmentation by a significant margin. Furthermore, our method can be readily usedfor a variety of complex image editing tasks, such as background removal and compositing.11Project Page: https://lukemelas.github.io/deep-spectral-segmentation/
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
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 Hungarian method for the assignment problem
Kuhn, H. W. (1955) · Naval Research Logistics Quarterly · doi:10.1002/nav.3800020109 · Cited by 13,120
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 · cited 2×
“We note that MaskContrast uses saliency masks from Deep-USPS [58], which was pre-trained with supervision using labeled data (Cityscapes [23]).”
BackgroundMethodRepresentation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242
Selective Search for Object Recognition
Uijlings, J. R. R., van de Sande, K. E. A., Gevers, T., & Smeulders, A. W. M. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0620-5 · Cited by 5,980
Context Encoders: Feature Learning by Inpainting
Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., & Efros, A. A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.278 · Cited by 5,691
Emerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00951 · Cited by 5,638 · cited 6×
“Numerous recent works [4, 8, 18] have observed that vision transformers perform exceptionally well relative to convolutional architectures in the self-supervised setting.”
BackgroundMethodInfluentialBootstrap Your Own Latent: A New Approach to Self-Supervised Learning
Grill, J.-B., Strub, F., Altché, F., Tallec, C., Richemond, P. H., Buchatskaya, E., Doersch, C., Pires, B. A., Guo, Z. D., Azar, M. G., et al. (2020) · arXiv · doi:10.48550/arxiv.2006.07733 · Cited by 3,846 · cited 3×
“[29,39] extract segmentations from pretrained generative models such as BigBiGAN.”
BackgroundMethodExploring Simple Siamese Representation Learning
Chen, X., & He, K. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01549 · Cited by 3,725
Unsupervised Feature Learning via Non-parametric Instance Discrimination
Wu, Z., Xiong, Y., Yu, S. X., & Lin, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00393 · Cited by 3,664
Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
Noroozi, M., & Favaro, P. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46466-4_5 · Cited by 2,775 · cited 1×
“Early research in this area was based on solving pretext tasks such as rotation, jigsaw puzzles, colorization, and inpainting [24, 27, 39, 59, 61, 62, 95, 96].”
BackgroundEdge Boxes: Locating Object Proposals from Edges
Zitnick, C. L., & Dollár, P. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_26 · Cited by 2,656
Unsupervised Visual Representation Learning by Context Prediction
Doersch, C., Gupta, A., & Efros, A. A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.167 · Cited by 2,629
Saliency Detection via Graph-Based Manifold Ranking
Yang, C., Zhang, L., Lu, H., Ruan, X., & Yang, M.-H. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.407 · Cited by 2,554 · cited 1×
“For single-object segmentation, we evaluate on four challenging benchmarks: CUB [81], DUTS [82], DUT-OMRON [89], and ECSSD [66].”
MethodUnsupervised Learning of Visual Features by Contrasting Cluster Assignments
Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020) · arXiv · doi:10.48550/arxiv.2006.09882 · Cited by 2,499
Unsupervised Representation Learning by Predicting Image Rotations
Gidaris, S., Singh, P., & Komodakis, N. (2018) · arXiv · doi:10.48550/arxiv.1803.07728 · Cited by 2,477 · cited 2×
“Early research in this area was based on solving pretext tasks such as rotation, jigsaw puzzles, colorization, and inpainting [24, 27, 39, 59, 61, 62, 95, 96].”
BackgroundTokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z., Tay, F. E., Feng, J., & Yan, S. (2021) · arXiv · doi:10.48550/arxiv.2101.11986 · Cited by 2,415
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z., Tay, F. E. H., Feng, J., & Yan, S. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00060 · Cited by 2,415 · cited 1×
“Numerous variants of the vision trans-former have been proposed, such as Deit [71], Token-to-Token ViT [90], DeepViT [98], CrossViT [11], PiT [35], CaiT [72], LeViT [28], CvT [85], and Swin/Twins [21,54].”
BackgroundTian, Y., Krishnan, D., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58621-8_45 · Cited by 1,997
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
Jia, C., Yang, Y., Xia, Y., Chen, Y.-T., Parekh, Z., Pham, H., Le, Q. V., Sung, Y., Li, Z., & Duerig, T. (2021) · arXiv · doi:10.48550/arxiv.2102.05918 · Cited by 1,977
An Empirical Study of Training Self-Supervised Vision Transformers
Chen, X., Xie, S., & He, K. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00950 · Cited by 1,648 · cited 3×
“Others distinguish themselves by removing the dependency on negative examples [17, 29, 91], the use of clustering [7, 52], and most recently, the extension to transformer architectures [8,18].”
BackgroundHypercolumns for object segmentation and fine-grained localization
Hariharan, B., Arbelaez, P., Girshick, R., & Malik, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298642 · Cited by 1,511 · cited 3×
“These features may be extracted from any part of the network and can even be a combination of different layers, i.e ., hyper-columns [31].”
BackgroundGoing deeper with Image Transformers
Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., & Jegou, H. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00010 · Cited by 1,259 · cited 1×
“Numerous variants of the vision trans-former have been proposed, such as Deit [71], Token-to-Token ViT [90], DeepViT [98], CrossViT [11], PiT [35], CaiT [72], LeViT [28], CvT [85], and Swin/Twins [21,54].”
BackgroundData-Efficient Image Recognition with Contrastive Predictive Coding
Hénaff, O. J., Srinivas, A., De Fauw, J., Razavi, A., Doersch, C., Eslami, S. M. A., & Oord, A. V. D. (2019) · arXiv · doi:10.48550/arxiv.1905.09272 · Cited by 1,014
LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference
Graham, B., El-Nouby, A., Touvron, H., Stock, P., Joulin, A., Jegou, H., & Douze, M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01204 · Cited by 935 · cited 3×
“For further reading in spectral graph theory, we encourage the reader to look into the following resources: [9,28,34,35].”
BackgroundMethodWhat makes for good views for contrastive learning
Tian, Y., Sun, C., Poole, B., Krishnan, D., Schmid, C., & Isola, P. (2020) · arXiv · doi:10.48550/arxiv.2005.10243 · Cited by 773
Dense Contrastive Learning for Self-Supervised Visual Pre-Training
Wang, X., Zhang, R., Shen, C., Kong, T., & Li, L. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00304 · Cited by 660
DeepViT: Towards Deeper Vision Transformer
Zhou, D., Kang, B., Jin, X., Yang, L., Lian, X., Jiang, Z., Hou, Q., & Feng, J. (2021) · arXiv · doi:10.48550/arxiv.2103.11886 · Cited by 398
Exploring Simple Siamese Representation Learning
Chen, X., & He, K. (2020) · arXiv · doi:10.48550/arxiv.2011.10566 · Cited by 381
Xie, Z., Lin, Y., Zhang, Z., Cao, Y., Lin, S., & Hu, H. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01641 · Cited by 370
MONet: Unsupervised Scene Decomposition and Representation
Burgess, C. P., Matthey, L., Watters, N., Kabra, R., Higgins, I., Botvinick, M., & Lerchner, A. (2019) · arXiv · doi:10.48550/arxiv.1901.11390 · Cited by 270
Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals
Van Gansbeke, W., Vandenhende, S., Georgoulis, S., & Van Gool, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00990 · Cited by 231 · cited 5×
“MaskContrast [74], the current state of the art in unsupervised semantic segmentation, uses saliency detection to find object segments ( i.e ., the foreground) and then learns pixel-wise embeddings via a contrastive objective.”
BackgroundMethodInfluentialSegSort: Segmentation by Discriminative Sorting of Segments
Hwang, J.-J., Yu, S., Shi, J., Collins, M., Yang, T.-J., Zhang, X., & Chen, L.-C. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00743 · Cited by 124 · cited 2×
“MaskContrast [38], the current state of the art in unsupervised semantic segmentation, uses saliency detection to find object segments ( i.e . the foreground) and then learns pixel-wise embeddings via a contrastive objective.”
BackgroundMethodLearning visual groups from co-occurrences in space and time
Isola, P., Zoran, D., Krishnan, D., & Adelson, E. H. (2015) · arXiv · doi:10.48550/arxiv.1511.06811 · Cited by 90
SiT: Self-supervised vIsion Transformer
Atito, S., Awais, M., & Kittler, J. (2021) · arXiv · doi:10.48550/arxiv.2104.03602 · Cited by 75 · cited 2×
“For single-object segmentation, generative methods currently rank as the most active research direction, with numerous works having been proposed in the last two years [3, 4, 8, 19, 20, 29, 39, 40].”
Background
Cited by
DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering
Aflalo, A., Bagon, S., Kashti, T., & Eldar, Y. (2023) · 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw60793.2023.00010 · Cited by 53
“Additionally, we incorporate deep features as node features for graph building, which is absent in previous meth-ods that solely used the correlation matrix of the deep features [8, 23, 34].”
BackgroundMethodInfluentialProbing the 3D Awareness of Visual Foundation Models
Banani, M. E., Raj, A., Maninis, K.-K., Kar, A., Li, Y., Rubinstein, M., Sun, D., Guibas, L., Johnson, J., & Jampani, V. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.02059 · Cited by 52
“Furthermore, the dense representations learned by such models extend beyond their training tasks and exhibit strong zero-shot capabilities in other tasks such as segmentation [56, 95] and part discovery [1, 27].”
BackgroundNeural Congealing: Aligning Images to a Joint Semantic Atlas
Ofri-Amar, D., Geyer, M., Kasten, Y., & Dekel, T. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01859 · Cited by 23
“Other works used the pre-trained features for both object localization and segmentation [29], and even object part discovery and segmentation [7].”
Method
Metadata
- Authors
- Melas-Kyriazi, L., Rupprecht, C., Laina, I., & Vedaldi, A.
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2022-06
- Pages
- 8354-8365
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4313150877
- Cited by
- 150
- References
- 40
- FWCI
- 12.75
- Type
- conference paper
- Language
- en
- Open access
- green
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.