Category-Level Adversarial Adaptation for Semantic Segmentation using Purified Features.
- Publisher:
- Institute of Electrical and Electronics Engineers
- Publication Type:
- Journal Article
- Citation:
- IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, PP, (8), pp. 3940-3956
- Issue Date:
- 2022-03-08
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
Category-Level Adversarial Adaptation for Semantic Segmentation using Purified Features..pdf | Published version | 5.16 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
We target the problem named unsupervised domain adaptive semantic segmentation. A key in this campaign consists in reducing the domain shift, so that a classifier based on labeled data from one domain can generalize well to other domains. With the advancement of adversarial learning framework, recent works prefer the strategy of aligning the marginal distribution in the feature spaces for minimizing the domain discrepancy. However, based on the observance in experiments, only focusing on aligning global marginal distribution but ignoring the local joint distribution alignment fails to be the optimal choice. Other than that, the noisy factors existing in the feature spaces, which are not relevant to the target task, entangle with the domain invariant factors improperly and make the domain distribution alignment more difficult. To address those problems, we introduce two new modules, Significance-aware Information Bottleneck (SIB) and Category-level alignment (CLA), to construct a purified embedding based category-level adversarial network. In three domain adaptation tasks, i.e., GTA5 -> Cityscapes, SYNTHIA -> Cityscapes and Cross Season, we validate that our proposed method matches the state of the art in segmentation accuracy.
Please use this identifier to cite or link to this item: