# Collaborative Learning for Enhanced Unsupervised Domain Adaptation

Source: [Collaborative Learning for Enhanced Unsupervised Domain Adaptation](<https://www.sota2.com/research/paper/68fa78031e209131cea76561>)

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

Data updated: 2025-10-26T04:30:26.676Z

Authors: Minhee Cho, Hyesong Choi, Hayeon Jo, Dongbo Min

Published: 2024-09-04T13:35:15.000Z

## Abstract

Unsupervised Domain Adaptation (UDA) endeavors to bridge the gap between a model trained on a labeled source domain and its deployment in an unlabeled target domain. However, current high-performance models demand significant resources, making deployment costs prohibitive and highlighting the need for compact, yet effective models. For UDA of lightweight models, Knowledge Distillation (KD) leveraging a Teacher-Student framework could be a common approach, but we found that domain shift in UDA leads to a significant increase in non-salient parameters in the teacher model, degrading model's generalization ability and transferring misleading information to the student model. Interestingly, we observed that this phenomenon occurs considerably less in the student model. Driven by this insight, we introduce Collaborative Learning for UDA (CLDA), a method that updates the teacher's non-salient parameters using the student model and at the same time utilizes the updated teacher model to improve UDA performance of the student model. Experiments show consistent performance improvements for both student and teacher models. For example, in semantic segmentation, CLDA achieves an improvement of +0.7% mIoU for the teacher model and +1.4% mIoU for the student model compared to the baseline model in the GTA-to-Cityscapes datasets. In the Synthia-to-Cityscapes dataset, it achieves an improvement of +0.8% mIoU and +2.0% mIoU for the teacher and student models, respectively.

## 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/2409.02699>)

[PDF](<https://arxiv.org/pdf/2409.02699.pdf>)
