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

TL;DR

The document outlines elsarticle.cls, a LaTeX document class tailored for Elsevier journals that builds on article.cls to reduce package conflicts and improve compatibility with common tools. It details the class's features, including robust frontmatter support (abstracts, keywords), integration with natbib and hyperref, and flexible formatting options for preprint and final styles. A thorough comparison with the older elsart.cls highlights improvements such as easier theorem environments and enhanced formatting controls, aiming to streamline manuscript preparation for Elsevier submissions. The installation guide covers obtaining the package from Elsevier resources or CTAN, generating the class file from source, and updating TeX systems, ensuring straightforward adoption by authors.

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.