Single Image Test-Time Adaptation for Segmentation
Not on the map. Why?
Abstract (arXiv)
Test-Time Adaptation (TTA) methods improve the robustness of deep neural networks to domain shift on a variety of tasks such as image classification or segmentation. This work explores adapting segmentation models to a single unlabelled image with no other data available at test-time. In particular, this work focuses on adaptation by optimizing self-supervised losses at test-time. Multiple baselines based on different principles are evaluated under diverse conditions and a novel adversarial training is introduced for adaptation with mask refinement. Our additions to the baselines result in a 3.51 and 3.28 % increase over non-adapted baselines, without these improvements, the increase would be 1.7 and 2.16 % only.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 36 of its 53 references that are in the map. First posted on arXiv 25 Sep 2023.
Builds on
36 of 53 references.
References · 36
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2016Layer Normalizationcited by 5,669
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
- 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
- 2016Adversarial examples in the physical worldcited by 1,769
- 2017Adversarial Discriminative Domain Adaptationcited by 1,311
24 more
- 2016Playing for Data: Ground Truth from Computer Gamescited by 818
- 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
- 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 569
- 2022Continual Test-Time Domain Adaptationcited by 525
- 2020Improving robustness against common corruptions by covariate shift adaptationcited by 431
- 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 415
- 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 335
- 2022Contrastive Test-Time Adaptationcited by 261
- 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 236
- 2022Test-Time Training with Masked Autoencoderscited by 212
- 2021Source-Free Domain Adaptation for Semantic Segmentationcited by 168
- 2020Test-Time Adaptable Neural Networks for Robust Medical Image Segmentationcited by 102
- 2022Back to the Source: Diffusion-Driven Test-Time Adaptationcited by 71
- 2021MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaptioncited by 65
- 2021A Prototype-Oriented Framework for Unsupervised Domain Adaptationcited by 62
- 2021SITA: Single Image Test-time Adaptationcited by 59
- 2018Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentationcited by 49
- 2019Domain Adaptation for Object Detection via Style Consistencycited by 45
- 2023Test-Time Training on Video Streamscited by 37
- 2020Rethinking Distributional Matching Based Domain Adaptationcited by 33
- 2022On the Road to Online Adaptation for Semantic Image Segmentationcited by 23
- 2023Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classificationcited by 17
- 2021AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Semantic Segmentationcited by 11
- 2021Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shiftscited by 7
Built on by
Citing papers per year: 2024: 1; 2025: 1; 2026: 1.
3 papers.