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

arXiv: https://arxiv.org/abs/2602.22621 · HTML: https://mlsanity.com/paper/2602.22621/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 30 of 30)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Bridging the Gap to Real-World Object-Centric Learning](https://mlsanity.com/paper/2209.14860/) (2022)
- [Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?](https://mlsanity.com/paper/1610.01983/) (2016)
- [Focal Modulation Networks](https://mlsanity.com/paper/2203.11926/) (2022)
- [Cross-Domain Adaptive Teacher for Object Detection](https://mlsanity.com/paper/2111.13216/) (2021)
- [Object-Centric Slot Diffusion](https://mlsanity.com/paper/2303.10834/) (2023)
- [A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data](https://mlsanity.com/paper/2012.05400/) (2020)
- [Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.15793/) (2022)
- [Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers](https://mlsanity.com/paper/2107.12636/) (2021)
- [MTTrans: Cross-Domain Object Detection with Mean-Teacher Transformer](https://mlsanity.com/paper/2205.01643/) (2022)
- [Adversarial Alignment for Source Free Object Detection](https://mlsanity.com/paper/2301.04265/) (2023)
- [Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentation](https://mlsanity.com/paper/2112.08949/) (2021)
- [Periodically Exchange Teacher-Student for Source-Free Object Detection](https://mlsanity.com/paper/2311.13930/) (2023)
- [CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection](https://mlsanity.com/paper/2403.19278/) (2024)
- [Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights](https://mlsanity.com/paper/2407.07586/) (2024)
- [Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation](https://mlsanity.com/paper/2407.13524/) (2024)
- [DATR: Unsupervised Domain Adaptive Detection Transformer with Dataset-Level Adaptation and Prototypical Alignment](https://mlsanity.com/paper/2405.11765/) (2024)
- [SlotGNN: Unsupervised Discovery of Multi-Object Representations and Visual Dynamics](https://mlsanity.com/paper/2310.04617/) (2023)
- [TITAN: Query-Token based Domain Adaptive Adversarial Learning](https://mlsanity.com/paper/2506.21484/) (2025)

## Abstract (arXiv)

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.