Can I read PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation on EtoBox?

PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation by Chen, Mu; Zheng, Zhedong; Yang, Yi; Chua, Tat-Seng is a scholarly article available to read on EtoBox.

What is PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation about?

Unsupervised Domain Adaptation (UDA) aims to enhance the generalization of the learned model to other domains. The domain-invariant knowledge is transferred from the model trained on labeled source domain, e.g., video game, to unlabeled target domains, e.g., real-world scenarios, saving annotation expenses. Existing UDA methods for semantic segmentation usually focus on minimizing the inter-domain discrepancy of various levels, e.g., pixels, features, and predictions, for extracting domain-invariant knowledge. However, the primary intra-domain knowledge, such as context correlation inside an image, remains underexplored. In an attempt to fill this gap, we propose a unified pixel- and patch-wise self-supervised learning framework, called PiPa, for domain adaptive semantic segmentation that facilitates intra-image pixel-wise correlations and patch-wise semantic consistency against different contexts. The proposed framework exploits the inherent structures of intra-domain images, which: (1) explicitly encourages learning the discriminative pixel-wise features with intra-class compactness and inter-class separability, and (2) motivates the robust feature learning of the identical patch

Author

Chen, Mu; Zheng, Zhedong; Yang, Yi; Chua, Tat-Seng

Published

2022

Language

EN