Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection Article Swipe

MAKE IMPACT

Vibashan VS , Poojan Oza , Vishal M. Patel · YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2203.15793

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 the 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 based knowledge distillation strategy to avoid overfitting to the noisy pseudo-labels generated by the source-trained model. 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 previous state-of-the-art domain adaptive detection methods. Code and models are provided in \href{https://viudomain.github.io/irg-sfda-web/}{https://viudomain.github.io/irg-sfda-web/}.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2203.15793

PDF

https://arxiv.org/pdf/2203.15793

OA Status

green

Cited By

7

Related Works

10

OpenAlex ID

https://openalex.org/W4221151970

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4221151970

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2203.15793

Digital Object Identifier

Title

Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2022

Year of publication

Publication date

2022-03-29

Full publication date if available

Authors

Vibashan VS, Poojan Oza, Vishal M. Patel

List of authors in order

Landing page

https://arxiv.org/abs/2203.15793

Publisher landing page

PDF URL

https://arxiv.org/pdf/2203.15793

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2203.15793

Direct OA link when available

Concepts

Computer science, Source code, Artificial intelligence, Domain (mathematical analysis), Overfitting, Relation (database), Object (grammar), Representation (politics), Benchmark (surveying), Graph, Object detection, Machine learning, Pattern recognition (psychology), Data mining, Theoretical computer science, Artificial neural network, Programming language, Political science, Politics, Law, Mathematics, Mathematical analysis, Geography, Geodesy

Top concepts (fields/topics) attached by OpenAlex

Cited by

7

Total citation count in OpenAlex

Citations by year (recent)

2024: 3, 2023: 4

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload