Source-Free Domain Adaptive Object Detection with Semantics Compensation

source-free-domain-adaptive-object-detection-with-semantics-compensation

Source-Free Domain Adaptive Object Detection with Semantics Compensation

[Submitted on 7 Oct 2024 (v1), last revised 6 Nov 2026 (this version, v4)]

View PDF HTML (experimental)

Abstract:Strong data augmentation is a fundamental component of state-of-the-art mean teacher-based Source-Free domain adaptive Object Detection (SFOD) methods, enabling consistency-based self-supervised optimization along weak augmentation. However, our theoretical analysis and empirical observations reveal a critical limitation: strong augmentation can inadvertently erase class-relevant components, leading to artificial inter-category confusion. To address this issue, we introduce Weak-to-strong Semantics Compensation (WSCo), a novel remedy that leverages weakly augmented images, which preserve full semantics, as anchors to enrich the feature space of their strongly augmented counterparts. Essentially, this compensates for the class-relevant semantics that may be lost during strong augmentation on the fly. Notably, WSCo can be implemented as a generic plug-in, easily integrable with any existing SFOD pipelines. Extensive experiments validate the negative impact of strong augmentation on detection performance, and the effectiveness of WSCo in enhancing the performance of previous detection models on standard benchmarks.

Submission history

From: Song Tang [view email]
[v1] Mon, 7 Oct 2024 23:32:06 UTC (48,174 KB)
[v2] Tue, 30 Sep 2025 00:30:01 UTC (8,266 KB)
[v3] Wed, 1 Oct 2025 02:19:09 UTC (8,266 KB)
[v4] Fri, 6 Nov 2026 12:14:53 UTC (8,266 KB)