# TMT: Cross-domain Semantic Segmentation with Region-adaptive Transferability Estimation

Source: [TMT: Cross-domain Semantic Segmentation with Region-adaptive Transferability Estimation](<https://www.sota2.com/research/paper/68fa7c1d1e209131cea8c726>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:56:14.357Z

Authors: Enming Zhang, Zhengyu Li, Yanru Wu, Jingge Wang, Yang Tan, Guan Wang, Yang Li, Xiaoping Zhang

Published: 2025-04-08T07:53:51.000Z

## Abstract

Recent advances in Vision Transformers (ViTs) have significantly advanced semantic segmentation performance. However, their adaptation to new target domains remains challenged by distribution shifts, which often disrupt global attention mechanisms. While existing global and patch-level adaptation methods offer some improvements, they overlook the spatially varying transferability inherent in different image regions. To address this, we propose the Transferable Mask Transformer (TMT), a region-adaptive framework designed to enhance cross-domain representation learning through transferability guidance. First, we dynamically partition the image into coherent regions, grouped by structural and semantic similarity, and estimates their domain transferability at a localized level. Then, we incorporate region-level transferability maps directly into the self-attention mechanism of ViTs, allowing the model to adaptively focus attention on areas with lower transferability and higher semantic uncertainty. Extensive experiments across 20 diverse cross-domain settings demonstrate that TMT not only mitigates the performance degradation typically associated with domain shift but also consistently outperforms existing approaches.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2504.05774>)

[PDF](<https://arxiv.org/pdf/2504.05774.pdf>)