Unsupervised Adaptive Semantic Segmentation with Local Lipschitz Constraint

TL;DR

This paper introduces a two-stage unsupervised domain adaptation method for semantic segmentation that uses a local Lipschitz constraint to improve domain alignment and reduce error propagation, achieving strong results on benchmarks.

Contribution

It proposes a novel non-adversarial approach utilizing local Lipschitz regularization for both domain alignment and self-learning in semantic segmentation.

Findings

Effective domain adaptation without adversarial training

Reduces error propagation in pseudo-labeling

Achieves state-of-the-art results on benchmarks

Abstract

Recent advances in unsupervised domain adaptation have seen considerable progress in semantic segmentation. Existing methods either align different domains with adversarial training or involve the self-learning that utilizes pseudo labels to conduct supervised training. The former always suffers from the unstable training caused by adversarial training and only focuses on the inter-domain gap that ignores intra-domain knowledge. The latter tends to put overconfident label prediction on wrong categories, which propagates errors to more samples. To solve these problems, we propose a two-stage adaptive semantic segmentation method based on the local Lipschitz constraint that satisfies both domain alignment and domain-specific exploration under a unified principle. In the first stage, we propose the local Lipschitzness regularization as the objective function to align different domains by exploiting intra-domain knowledge, which explores a promising direction for non-adversarial adaptive semantic segmentation. In the second stage, we use the local Lipschitzness regularization to estimate the probability of satisfying Lipschitzness for each pixel, and then dynamically sets the threshold of pseudo labels to conduct self-learning. Such dynamical self-learning effectively avoids the error propagation caused by noisy labels. Optimization in both stages is based on the same principle, i.e., the local Lipschitz constraint, so that the knowledge learned in the first stage can be maintained in the second stage. Further, due to the model-agnostic property, our method can easily adapt to any CNN-based semantic segmentation networks. Experimental results demonstrate the excellent performance of our method on standard benchmarks.