CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object Detection

2026-02-25

AI Summary

This work addresses the neglect of object-level structural information in source-free domain adaptive object detection by proposing a novel object-centric learning approach. Built upon the DETR architecture, the method introduces a Hierarchical Slot Attention (HSA) module to decompose images into structured slot representations and incorporates a Class-Guided Slot Contrast (CGSC) mechanism to enhance cross-domain semantic consistency and domain invariance. By integrating pseudo-label refinement with contrastive learning, the proposed framework significantly outperforms existing methods across multiple cross-domain benchmarks. This study is the first to leverage slot representations and object-centric learning for source-free domain adaptive object detection, demonstrating its effectiveness and superiority, particularly in privacy-sensitive scenarios.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Object Detection & Categorization
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Source-Free Domain Adaptive Object Detection (SF-DAOD) aims to adapt a detector trained on a labeled source domain to an unlabeled target domain without retaining any source data. Despite recent progress, most popular approaches focus on tuning pseudo-label thresholds or refining the teacher-student framework, while overlooking object-level structural cues within cross-domain data. In this work, we present CGSA, the first framework that brings Object-Centric Learning (OCL) into SF-DAOD by integrating slot-aware adaptation into the DETR-based detector. Specifically, our approach integrates a Hierarchical Slot Awareness (HSA) module into the detector to progressively disentangle images into slot representations that act as visual priors. These slots are then guided toward class semantics via a Class-Guided Slot Contrast (CGSC) module, maintaining semantic consistency and prompting domain-invariant adaptation. Extensive experiments on multiple cross-domain datasets demonstrate that our approach outperforms previous SF-DAOD methods, with theoretical derivations and experimental analysis further demonstrating the effectiveness of the proposed components and the framework, thereby indicating the promise of object-centric design in privacy-sensitive adaptation scenarios. Code is released at https://github.com/Michael-McQueen/CGSA.

Problem

• Source-Free Domain Adaptation
• Object Detection
• Object-Centric Learning
• Cross-Domain Adaptation
• Semantic Consistency

Innovation

• Object-Centric Learning
• Source-Free Domain Adaptation
• Slot Representation
• Class-Guided Contrast
• DETR-based Detector