홈 › Papers

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

2024-10-11 · Haochen Li, Rui Zhang, Hantao Yao, Xin Zhang, Yifan Hao, Xinkai Song, Xiaqing Li, Yongwei Zhao, Ling Li, Yunji Chen

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, i.e., 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.

📄 PDF Abstract BibTeX arXiv:2410.09004

Code (1)

therock90421/da-ada 공식 구현 pytorch

Tasks

General Knowledge object-detection Object Detection

Methods 이 논문이 사용한 방법론

Adapter 설명 없음

Universal Domain Adaptive Object Detector

2022-07-05 · Wenxu Shi, Lei Zhang, WeiJie Chen, ShiLiang Pu

Universal domain adaptive object detection (UniDAOD)is more challenging than domain adaptive object detection (DAOD) since the label space of the source domain may not be the same as that of the target and the scale of o…

Multi-Label Learning Object object-detection Object Detection

AdaSports-Traj: Role- and Domain-Aware Adaptation for Multi-Agent Trajectory Modeling in Sports

2025-09-19 · Yi Xu, Yun Fu arxiv

Trajectory prediction in multi-agent sports scenarios is inherently challenging due to the structural heterogeneity across agent roles (e.g., players vs. ball) and dynamic distribution gaps across different sports domain…

Trajectory Prediction Contrastive Learning Trajectory Modeling

Co-Adaptive Multi-Task LoRA: Transfer-Aware, Label-Free Control of Domain Participation

2026-07-03 · Wei Zhang, Lin Tang, Ming Zhao, Yuxuan Wang arxiv

Fine-tuning a single low-rank adapter on many domains at once is multi-task learning: the domains must be co-learned, and how they share the adapter decides whether they help or hurt one another. Most efficient fine-tuni…

Multi-Task Learning

Leveraging Normalization Layer in Adapters With Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learning

2023-12-18 · Yongjin Yang, Taehyeon Kim, Se-Young Yun

Cross-domain few-shot learning presents a formidable challenge, as models must be trained on base classes and then tested on novel classes from various domains with only a few samples at hand. While prior approaches have…

Cross-Domain Few-Shot cross-domain few-shot learning Few-Shot Learning

TADA: Efficient Task-Agnostic Domain Adaptation for Transformers

2023-05-22 · Chia-Chien Hung, Lukas Lange, Jannik Strötgen

Intermediate training of pre-trained transformer-based language models on domain-specific data leads to substantial gains for downstream tasks. To increase efficiency and prevent catastrophic forgetting alleviated from f…

Domain Adaptation