Towards Adaptive Semantic Segmentation by Progressive Feature Refinement

TL;DR

This paper introduces a progressive feature refinement framework combined with domain adversarial learning to improve the transferability of semantic segmentation models across different domains, addressing practical deployment challenges.

Contribution

It proposes a novel progressive feature refinement method with domain adversarial training to enhance domain adaptation in semantic segmentation.

Findings

Outperforms state-of-the-art domain adaptation methods

Maintains stable performance across different target domains

Effective multi-stage feature alignment improves transferability

Abstract

As one of the fundamental tasks in computer vision, semantic segmentation plays an important role in real world applications. Although numerous deep learning models have made notable progress on several mainstream datasets with the rapid development of convolutional networks, they still encounter various challenges in practical scenarios. Unsupervised adaptive semantic segmentation aims to obtain a robust classifier trained with source domain data, which is able to maintain stable performance when deployed to a target domain with different data distribution. In this paper, we propose an innovative progressive feature refinement framework, along with domain adversarial learning to boost the transferability of segmentation networks. Specifically, we firstly align the multi-stage intermediate feature maps of source and target domain images, and then a domain classifier is adopted to discriminate the segmentation output. As a result, the segmentation models trained with source domain images can be transferred to a target domain without significant performance degradation. Experimental results verify the efficiency of our proposed method compared with state-of-the-art methods.