Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3520-3530
Abstract
Unsupervised Domain Adaptation (UDA) is an effective approach to tackle the issue of domain shift. Specifically, UDA methods try to align the source and target representations to improve generalization on the target domain. Further, UDA methods work under the assumption that the source data is accessible during the adaptation process. However, in real-world scenarios, the labelled source data is often restricted due to privacy regulations, data transmission constraints, or proprietary data concerns. The Source-Free Domain Adaptation (SFDA) setting aims to alleviate these concerns by adapting a source-trained model for the target domain without requiring access to the source data. In this paper, we explore the SFDA setting for the task of adaptive object detection. To this end, we propose a novel training strategy for adapting a source-trained object detector to the target domain without source data. More precisely, we design a novel contrastive loss to enhance the target representations by exploiting the objects relations for a given target domain input. These object instance relations are modelled using an Instance Relation Graph (IRG) network, which are then used to guide the contrastive representation learning. In addition, we utilize a student-teacher to effectively distill knowledge from source-trained model to target domain. Extensive experiments on multiple object detection benchmark datasets show that the proposed approach is able to efficiently adapt source-trained object detectors to the target domain, outperforming state-of-the-art domain adaptive detection methods. Code and models are provided in https://viudomain.github.io/irg-sfda-web/.Keywords
All Related Versions
This publication has 50 references indexed in Scilit:
- A Comprehensive Survey of Graph Embedding: Problems, Techniques, and ApplicationsIEEE Transactions on Knowledge and Data Engineering, 2018
- Focal Loss for Dense Object Detection2017
- No More Discrimination: Cross City Adaptation of Road Scene Segmenters2017
- Adversarial Discriminative Domain Adaptation2017
- Deep Residual Learning for Image Recognition2016
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- A new model for learning in graph domains2006