SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.09004 · NeurIPS · 2024

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

Rui Zhang, Xin Zhang, Yunji Chen, Ling Li, Haochen Li, Hantao Yao, Xinkai Song, Yifan Hao, Yongwei Zhao, Xiaqing Li

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
Therock90421/DA-Ada canonical 4 of 6
FunctionStatusWhere it lives
convert_basic_c2_names Ran Therock90421/DA-Ada/detectron2/checkpoint/c2_model_loading.py
code served (permissive licence) · get_code("e8526a516b4f9206")
convert_basic_clip_names Ran Therock90421/DA-Ada/detectron2/checkpoint/clip_model_loading.py
code served (permissive licence) · get_code("7b7f6e4aa28b1a69")
convert_c2_detectron_names Ran Therock90421/DA-Ada/detectron2/checkpoint/c2_model_loading.py
code served (permissive licence) · get_code("e36f87059208bb7e")
convert_clip_names Ran Therock90421/DA-Ada/detectron2/checkpoint/clip_model_loading.py
code served (permissive licence) · get_code("376248f5d186a885")
align_and_update_state_dicts Not yet run Therock90421/DA-Ada/detectron2/checkpoint/c2_model_loading.py
code served (permissive licence) · get_code("ac2638463572c152")
align_and_update_state_dicts_for_CLIP Not yet run Therock90421/DA-Ada/detectron2/checkpoint/clip_model_loading.py
code served (permissive licence) · get_code("0bd7b0a60b4069f9")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 domaininvariant 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

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.09004")
get_code_for_paper("2410.09004")
have("2410.09004")

Connect an agent — have() is free.