Exploiting Negative Learning for Implicit Pseudo Label Rectification in Source-Free Domain Adaptive Semantic Segmentation

It is desirable to transfer the knowledge stored in a well-trained source model onto non-annotated target domain in the absence of source data. However, state-of-the-art methods for source free domain adaptation (SFDA) are subject to strict limits: 1) access to internal specifications of source models is a must; and 2) pseudo labels should be clean during self-training, making critical tasks relying on semantic segmentation unreliable. Aiming at these pitfalls, this study develops a domain adaptive solution to semantic segmentation with pseudo label rectification (namely textitPR-SFDA), which operates in two phases: 1) textitConfidence-regularized unsupervised learning: Maximum squares loss applies to regularize the target model to ensure the confidence in prediction; and 2) textitNoise-aware pseudo label learning: Negative learning enables tolerance to noisy pseudo labels in training, meanwhile positive learning achieves fast convergence. Extensive experiments have been performed on domain adaptive semantic segmentation benchmark, textitGTA5 → Cityscapes. Overall, textitPR-SFDA achieves a performance of 49.0 mIoU, which is very close to that of the state-of-the-art counterparts. Note that the latter demand accesses to the source model's internal specifications, whereas the textitPR-SFDA solution needs none as a sharp contrast.