Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation

By Yahao Liu, Jinhong Deng, Jiale Tao, Tong Chu, Lixin Duan, Wen Li. 2022

25 citations recorded by the source corpus.

Existing works typically treat cross-domain semantic segmentation (CDSS) as a data distribution mismatch prob-lem and focus on aligning the marginal distribution or con-ditional distribution. However, the label shift issue is un-fortunately overlooked, which actually commonly exists in the CDSS task, and often causes a classifier bias in the learnt model. In this paper, we give an in-depth analysis and show that the damage of label shift can be overcome by aligning the data conditional distribution and correcting the posterior probability. To this end, we propose a novel approach to undo the damage of the label shift problem in CDSS. In implementation, we adopt class-level feature alignment for conditional distribution alignment, as well as two simple yet effective methods to rectify the classifier bias from source to target by remolding the classifier predictions. We conduct extensive experiments on the benchmark datasets of urban scenes, including GTA5 to Cityscapes and SYNTHIA to Cityscapes, where our proposed approach outperforms previous methods by a large margin. For instance, our model equipped with a self-training strat-egy reaches 59.3% mIoU on GTA5 to Cityscapes, pushing to a new state-of-the-art. The code will be available at https://github.com/manmanjun/Undoing_UDA.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Zhen Fang
  2. Xiao Wang
  3. Lixu Wang
  4. Qi Zhu
  5. Shichao Xu
  6. Jiahua Dong
  7. Gan Sun

In Computer Vision and Pattern Recognition

  1. Zhen Fang
  2. Xiao Wang
  3. Lixu Wang
  4. Qi Zhu
  5. Shichao Xu
  6. Jiahua Dong
  7. Gan Sun

Citations in the corpus