Consistency Regularization for Domain Adaptation
Not on the map. Why?
Abstract (arXiv)
Collection of real world annotations for training semantic segmentation models is an expensive process. Unsupervised domain adaptation (UDA) tries to solve this problem by studying how more accessible data such as synthetic data can be used to train and adapt models to real world images without requiring their annotations. Recent UDA methods applies self-learning by training on pixel-wise classification loss using a student and teacher network. In this paper, we propose the addition of a consistency regularization term to semi-supervised UDA by modelling the inter-pixel relationship between elements in networks' output. We demonstrate the effectiveness of the proposed consistency regularization term by applying it to the state-of-the-art DAFormer framework and improving mIoU19 performance on the GTA5 to Cityscapes benchmark by 0.8 and mIou16 performance on the SYNTHIA to Cityscapes benchmark by 1.2.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 29 of its 37 references that are in the map. First posted on arXiv 23 Aug 2022.
Builds on
29 of 37 references.
References · 29
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
- 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
- 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
- 2016Pyramid Scene Parsing Networkcited by 2,472
17 more
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
- 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
- 2017Adversarial Discriminative Domain Adaptationcited by 1,309
- 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
- 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
- 2016Playing for Data: Ground Truth from Computer Gamescited by 816
- 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
- 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
- 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
- 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
- 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
- 2019Interpolation Consistency Training for Semi-Supervised Learningcited by 248
- 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
- 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
- 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 176
- 2020Structured Consistency Loss for semi-supervised semantic segmentationcited by 39
- 2014Subspace Alignment For Domain Adaptationcited by 10
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.