Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning

TL;DR

This paper introduces a novel Cross-Domain Semi-Supervised Learning framework for object detection that leverages pseudo labels and fine-grained domain transfer to effectively adapt models across different domains without labels.

Contribution

It proposes the CDSSL framework with strategies like label sharpening and imbalanced sampling to address domain content gaps and pseudo label noise, outperforming prior methods.

Findings

Achieves 2.2% to 9.5% higher mAP than previous methods.

Effectively reduces domain content gap beyond style adaptation.

Demonstrates robustness across various domain shift scenarios.

Abstract

Current state-of-the-art object detectors can have significant performance drop when deployed in the wild due to domain gaps with training data. Unsupervised Domain Adaptation (UDA) is a promising approach to adapt models for new domains/environments without any expensive label cost. However, without ground truth labels, most prior works on UDA for object detection tasks can only perform coarse image-level and/or feature-level adaptation by using adversarial learning methods. In this work, we show that such adversarial-based methods can only reduce the domain style gap, but cannot address the domain content distribution gap that is shown to be important for object detectors. To overcome this limitation, we propose the Cross-Domain Semi-Supervised Learning (CDSSL) framework by leveraging high-quality pseudo labels to learn better representations from the target domain directly. To enable SSL for cross-domain object detection, we propose fine-grained domain transfer, progressive-confidence-based label sharpening and imbalanced sampling strategy to address two challenges: (i) non-identical distribution between source and target domain data, (ii) error amplification/accumulation due to noisy pseudo labeling on the target domain. Experiment results show that our proposed approach consistently achieves new state-of-the-art performance (2.2% - 9.5% better than prior best work on mAP) under various domain gap scenarios. The code will be released.