Versatile Teacher: A Class-aware Teacher-student Framework for Cross-domain Adaptation

TL;DR

This paper introduces Versatile Teacher, a class-aware teacher-student framework for cross-domain object detection that improves pseudo-label reliability and instance-level alignment, especially for one-stage detectors, addressing class imbalance and domain shift issues.

Contribution

The paper proposes a novel class-aware teacher-student model with CAPS for better pseudo-label selection and instance-level alignment tailored for one-stage detectors, enhancing cross-domain detection performance.

Findings

Achieves improved accuracy on three benchmark datasets.

Extends alignment techniques to popular one-stage detectors.

Demonstrates practical effectiveness with promising results.

Abstract

Addressing the challenge of domain shift between datasets is vital in maintaining model performance. In the context of cross-domain object detection, the teacher-student framework, a widely-used semi-supervised model, has shown significant accuracy improvements. However, existing methods often overlook class differences, treating all classes equally, resulting in suboptimal results. Furthermore, the integration of instance-level alignment with a one-stage detector, essential due to the absence of a Region Proposal Network (RPN), remains unexplored in this framework. In response to these shortcomings, we introduce a novel teacher-student model named Versatile Teacher (VT). VT differs from previous works by considering class-specific detection difficulty and employing a two-step pseudo-label selection mechanism, referred to as Class-aware Pseudo-label Adaptive Selection (CAPS), to generate more reliable pseudo labels. These labels are leveraged as saliency matrices to guide the discriminator for targeted instance-level alignment. Our method demonstrates promising results on three benchmark datasets, and extends the alignment methods for widely-used one-stage detectors, presenting significant potential for practical applications. Code is available at https://github.com/RicardooYoung/VersatileTeacher.