Contrastive Learning for Label Efficient Semantic Segmentation
The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have achieved impressive results by using large amounts of labeled training data, their performance drops significantly as the amount of labeled data decreases. This happens because deep CNNs trained with the de facto cross-entropy loss can easily overfit to small amounts of labeled data. To address this issue, we propose a simple and effective contrastive learning-based training strategy in which we first pretrain the network using a pixel-wise, label-based contrastive loss, and then fine-tune it using the cross-entropy loss. This approach increases intra-class compactness and inter-class separability, thereby resulting in a better pixel classifier. We demonstrate the effectiveness of the proposed training strategy using the Cityscapes and PASCAL VOC 2012 segmentation datasets. Our results show that pretraining with the proposed contrastive loss results in large performance gains (more than 20% absolute improvement in some settings) when the amount of labeled data is limited. In many settings, the proposed contrastive pretraining strategy, which does not use any additional data, is able to match or outperform the widely-used ImageNet pretraining strategy that uses more than a million additional labeled images.
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2016) · arXiv · doi:10.48550/arxiv.1606.00915 · Cited by 22,392
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
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · arXiv · doi:10.48550/arxiv.1802.02611 · Cited by 20,063
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_49 · Cited by 20,054
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
Self-citationThe 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
The Pascal Visual Object Classes Challenge: A Retrospective
Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-014-0733-5 · Cited by 7,139 · cited 1×
“PASCAL VOC 2012 [16]: This dataset consists of 10,582 training, 1,449 validation, and 456 test images with annotations for one background and 20 foreground object classes.”
MethodDimensionality Reduction by Learning an Invariant Mapping
Hadsell, R., Chopra, S., & LeCun, Y. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.100 · Cited by 5,336
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
Supervised Contrastive Learning
Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C., & Krishnan, D. (2020) · arXiv · doi:10.48550/arxiv.2004.11362 · Cited by 3,569 · cited 8×
“Recently, several approaches based on contrastive loss [22] have been proposed for self-supervised visual representation learning [9, 10, 14, 24, 35, 57, 60].”
BackgroundMethodInfluentialLearning Hierarchical Features for Scene Labeling
Farabet, C., Couprie, C., Najman, L., & LeCun, Y. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.231 · Cited by 2,620
Tian, Y., Krishnan, D., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58621-8_45 · Cited by 1,997
Object-Contextual Representations for Semantic Segmentation
Yuan, Y., Chen, X., & Wang, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58539-6_11 · Cited by 1,285
ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
Lin, D., Dai, J., Jia, J., He, K., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.344 · Cited by 1,129 · cited 1×
“To address this issue, several existing works use the large-scale ImageNet classification dataset for pretraining their models, and also leverage additional weaker forms of supervision such as image-level labels [1, 26, 34, 42], bounding boxes [12, 31, 42, 47], scribbles [36, 50] and points [2], or unlabeled images [5…”
MethodDense 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
Prototypical Contrastive Learning of Unsupervised Representations
Li, J., Zhou, P., Xiong, C., & Hoi, S. C. H. (2020) · arXiv · doi:10.48550/arxiv.2005.04966 · Cited by 611
Exploring Cross-Image Pixel Contrast for Semantic Segmentation
Wang, W., Zhou, T., Yu, F., Dai, J., Konukoglu, E., & Gool, L. V. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00721 · Cited by 604
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
Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation
Chen, L.-C., Lopes, R. G., Cheng, B., Collins, M. D., Cubuk, E. D., Zoph, B., Adam, H., & Shlens, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58545-7_40 · Cited by 165
Gaussian Conditional Random Field Network for Semantic Segmentation
Vemulapalli, R., Tuzel, O., Liu, M.-Y., & Chellappa, R. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.351 · Cited by 150 · cited 1×
“Semantic segmentation Since CNNs have been introduced to solve the semantic segmentation problem [17, 38], several deep CNN-based approaches have been proposed that gradually improved the performance [6, 7, 8, 21, 53, 61, 62, 63, 64] using large amounts of pixel-level annotations.”
Self-citationSegmentation-Aware Convolutional Networks Using Local Attention Masks
Harley, A. W., Derpanis, K. G., & Kokkinos, I. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.539 · Cited by 142 · cited 1×
“A few existing works [3, 18, 23, 33] use metric learning based on independent pairwise similarity and dissimilarity losses for the tasks of semantic and instance segmentation.”
MethodSegSort: 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 by
Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
Wang, Y., Wang, H., Shen, Y., Fei, J., Li, W., Jin, G., Wu, L., Zhao, R., & Le, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00421 · Cited by 504
Denoising Pretraining for Semantic Segmentation
Brempong, E. A., Kornblith, S., Chen, T., Parmar, N., Minderer, M., & Norouzi, M. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00462 · Cited by 120
Metadata
- Authors
- Zhao, X., Vemulapalli, R., Mansfield, P. A., Gong, B., Green, B., Shapira, L., & Wu, Y.
- Venue
- 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2021-10
- Pages
- 10603-10613
- OpenAlex
- W3113328489
- Cited by
- 175
- References
- 23
- FWCI
- 17.15
- Type
- conference paper
- Language
- en
- Open access
- closed
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.