DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection

Published: 25 Sept 2024, Last Modified: 27 Dec 2024NeurIPS 2024 posterEveryoneRevisionsBibTeXCC BY-NC-SA 4.0
Keywords: Unsupervised domain adaptation; Object detection; Visual-language model
TL;DR: We propose a novel Domain-Aware Adapter (DA-Ada) to exploit domain-invariant and domain-specific knowledge with the vision-language models for domain adaptive object detection.
Abstract: Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. As the visual-language models (VLMs) can provide essential general knowledge on unseen images, freezing the visual encoder and inserting a domain-agnostic adapter can learn domain-invariant knowledge for DAOD. However, the domain-agnostic adapter is inevitably biased to the source domain. It discards some beneficial knowledge discriminative on the unlabelled domain, \ie domain-specific knowledge of the target domain. To solve the issue, we propose a novel Domain-Aware Adapter (DA-Ada) tailored for the DAOD task. The key point is exploiting domain-specific knowledge between the essential general knowledge and domain-invariant knowledge. DA-Ada consists of the Domain-Invariant Adapter (DIA) for learning domain-invariant knowledge and the Domain-Specific Adapter (DSA) for injecting the domain-specific knowledge from the information discarded by the visual encoder. Comprehensive experiments over multiple DAOD tasks show that DA-Ada can efficiently infer a domain-aware visual encoder for boosting domain adaptive object detection. Our code is available at https://github.com/Therock90421/DA-Ada.
Supplementary Material: zip
Primary Area: Machine vision
Submission Number: 6320
Loading