# CSCL: Critical Semantic-Consistent Learning for Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2008.10464 · HTML: https://mlsanity.com/paper/2008.10464/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2020.

## Built on by (most cited first, 23 of 23)

- [Self-supervised Augmentation Consistency for Adapting Semantic Segmentation](https://mlsanity.com/paper/2105.00097/) (2021)
- [Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.11249/) (2021)
- [ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation](https://mlsanity.com/paper/2111.15242/) (2021)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Learning Bounds for Open-Set Learning](https://mlsanity.com/paper/2106.15792/) (2021)
- [Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images](https://mlsanity.com/paper/2108.12611/) (2021)
- [Meta Two-Sample Testing: Learning Kernels for Testing with Limited Data](https://mlsanity.com/paper/2106.07636/) (2021)
- [Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles](https://mlsanity.com/paper/2103.14098/) (2021)
- [Towards Novel Target Discovery Through Open-Set Domain Adaptation](https://mlsanity.com/paper/2105.02432/) (2021)
- [Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation](https://mlsanity.com/paper/2203.01074/) (2022)
- [Semi-supervised Domain Adaptive Structure Learning](https://mlsanity.com/paper/2112.06161/) (2021)
- [Unsupervised Adaptation of Semantic Segmentation Models without Source Data](https://mlsanity.com/paper/2112.02359/) (2021)
- [Unsupervised Contrastive Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2204.08399/) (2022)
- [SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets](https://mlsanity.com/paper/2308.11880/) (2023)
- [Dynamic Feature Alignment for Semi-supervised Domain Adaptation](https://mlsanity.com/paper/2110.09641/) (2021)
- [Unsupervised Dense Deformation Embedding Network for Template-Free Shape Correspondence](https://mlsanity.com/paper/2108.11609/) (2021)
- [Continual Domain Adaptation through Pruning-aided Domain-specific Weight Modulation](https://mlsanity.com/paper/2304.07560/) (2023)
- [Unsupervised Reinforcement Adaptation for Class-Imbalanced Text Classification](https://mlsanity.com/paper/2205.13139/) (2022)
- [MLN-net: A multi-source medical image segmentation method for clustered microcalcifications using multiple layer normalization](https://mlsanity.com/paper/2309.02742/) (2023)
- [ADeLA: Automatic Dense Labeling with Attention for Viewpoint Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2107.14285/) (2021)
- [A Mutation-based Text Generation for Adversarial Machine Learning Applications](https://mlsanity.com/paper/2212.11808/) (2022)
- [Robust Unsupervised Domain Adaptation by Retaining Confident Entropy via Edge Concatenation](https://mlsanity.com/paper/2310.07149/) (2023)
- [Heuristic Self-Paced Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions](https://mlsanity.com/paper/2603.24322/) (2026)

## Abstract (arXiv)

Unsupervised domain adaptation without consuming annotation process for unlabeled target data attracts appealing interests in semantic segmentation. However, 1) existing methods neglect that not all semantic representations across domains are transferable, which cripples domain-wise transfer with untransferable knowledge; 2) they fail to narrow category-wise distribution shift due to category-agnostic feature alignment. To address above challenges, we develop a new Critical Semantic-Consistent Learning (CSCL) model, which mitigates the discrepancy of both domain-wise and category-wise distributions. Specifically, a critical transfer based adversarial framework is designed to highlight transferable domain-wise knowledge while neglecting untransferable knowledge. Transferability-critic guides transferability-quantizer to maximize positive transfer gain under reinforcement learning manner, although negative transfer of untransferable knowledge occurs. Meanwhile, with the help of confidence-guided pseudo labels generator of target samples, a symmetric soft divergence loss is presented to explore inter-class relationships and facilitate category-wise distribution alignment. Experiments on several datasets demonstrate the superiority of our model.