Active Domain Adaptation

Active domain adaptation (ADA) aims to improve the performance of machine learning models on a new, related dataset (target domain) by strategically selecting a small subset of target data for annotation and using it to refine a model pre-trained on a different dataset (source domain). Current research focuses on efficient sample selection strategies, often incorporating uncertainty estimation and measures of domain discrepancy to identify the most informative samples, and on developing algorithms that effectively leverage these selected samples to bridge the gap between source and target domains. ADA's significance lies in its potential to reduce the substantial cost and effort associated with data annotation in various applications, particularly in fields like medical image analysis and robotics, where labeled data is scarce and expensive to obtain.

Papers

July 26, 2024

Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence
Mengyao Lyu, Tianxiang Hao, Xinhao Xu, Hui Chen, Zijia Lin, Jungong Han, Guiguang Ding
Domain Adaptation Active Learning Contrastive Method Continual Adaptation Active Domain Adaptation Cross Domain Alignment Neural Persistence

December 15, 2023

Density Matters: Improved Core-set for Active Domain Adaptive Segmentation
Shizhan Liu, Zhengkai Jiang, Yuxi Li, Jinlong Peng, Yabiao Wang, Weiyao Lin
Semantic Segmentation Greedy Algorithm Particle Density Active Domain Adaptation Core Set

November 21, 2023

Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer
Wenqiao Zhang, Zheqi Lv, Hao Zhou, Jia-Wei Liu, Juncheng Li, Mengze Li, Siliang Tang, Yueting Zhuang
Domain Shift Domain Transfer Active Domain Adaptation Uncertain Domain Uncertain Sample

September 23, 2023

Dual-Reference Source-Free Active Domain Adaptation for Nasopharyngeal Carcinoma Tumor Segmentation across Multiple Hospitals
Hongqiu Wang, Jian Chen, Shichen Zhang, Yuan He, Jinfeng Xu, Mengwan Wu, Jinlan He, Wenjun Liao, Xiangde Luo
Domain Adaptation Clinical Datasets Active Domain Adaptation Nasopharyngeal Carcinoma Gross Tumor Volume

July 26, 2023

Dynamic Domain Discrepancy Adjustment for Active Multi-Domain Adaptation
Long Liu, Bo Zhou, Zhipeng Zhao, Zening Liu
Domain Adaptation Source Domain Domain Discrepancy Active Domain Adaptation

July 21, 2023

Divide and Adapt: Active Domain Adaptation via Customized Learning
Duojun Huang, Jichang Li, Weikai Chen, Junshi Huang, Zhenhua Chai, Guanbin Li
Domain Adaptation Unsupervised Domain Adaptation Semi Supervised Domain Adaptation Data Divide Personalized Learning Active Domain Adaptation Domain Adaption

May 8, 2023

Generalized Universal Domain Adaptation with Generative Flow Networks
Didi Zhu, Yinchuan Li, Yunfeng Shao, Jianye Hao, Fei Wu, Kun Kuang, Jun Xiao, Chao Wu
Unsupervised Domain Adaptation Generative Flow Network Universal Domain Adaptation Active Domain Adaptation

April 26, 2023

Cluster Entropy: Active Domain Adaptation in Pathological Image Segmentation
Xiaoqing Liu, Kengo Araki, Shota Harada, Akihiko Yoshizawa, Kazuhiro Terada, Mariyo Kurata, Naoki Nakajima, Hiroyuki Abe, Tetsuo Ushiku, Ryoma Bise
Domain Adaptation Unsupervised Domain Adaptation Semi Supervised Domain Adaptation Active Domain Adaptation Pathological Segmentation

April 14, 2023

Spectral Transfer Guided Active Domain Adaptation For Thermal Imagery
Berkcan Ustun, Ahmet Kagan Kaya, Ezgi Cakir Ayerden, Fazil Altinel
Thermal Image Active Domain Adaptation Spectral Translation Spectral Resolution

March 9, 2023

Active Learning Based Domain Adaptation for Tissue Segmentation of Histopathological Images
Saul Fuster, Farbod Khoraminia, Trygve Eftestøl, Tahlita C. M. Zuiverloon, Kjersti Engan
Active Learning Histopathological Image Image Analysis Accurate Segmentation Selective Annotation Tissue Segmentation Active Domain Adaptation

February 27, 2023

Dirichlet-based Uncertainty Calibration for Active Domain Adaptation
Mixue Xie, Shuang Li, Rui Zhang, Chi Harold Liu
Cross Domain Target Domain Model Adaptation Active Domain Adaptation

October 13, 2022

Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain Shift
Sharat Agarwal, Saket Anand, Chetan Arora
Semantic Segmentation Domain Adaptation Active Learning Domain Shift Annotation Budget Active Domain Adaptation Augmentation Approach Annotation Effort

August 26, 2022

Local Context-Aware Active Domain Adaptation
Tao Sun, Cheng Lu, Haibin Ling
Domain Gap Local Context Active Domain Adaptation Contextual Adapter

August 13, 2022

Combating Label Distribution Shift for Active Domain Adaptation
Sehyun Hwang, Sohyun Lee, Sungyeon Kim, Jungseul Ok, Suha Kwak
Domain Adaptation Label Distribution Active Domain Adaptation Label Distribution Shift Distribution Mismatch Unlabeled Target

May 23, 2022

Active Domain Adaptation with Multi-level Contrastive Units for Semantic Segmentation
Hao Zhang, Ruimao Zhang, Zhanglin Peng, Junle Wang, Yanqing Jing
Contrastive Learning Semantic Segmentation Domain Adaptation Semi Supervised Domain Adaptation Domain Adaptation Task Active Domain Adaptation

April 25, 2022

Loss-based Sequential Learning for Active Domain Adaptation
Kyeongtak Han, Youngeun Kim, Dongyoon Han, Sungeun Hong
Domain Adaptation Sequential Learning Query Learning Active Domain Adaptation

March 11, 2022

Learning Distinctive Margin toward Active Domain Adaptation
Ming Xie, Yuxi Li, Yabiao Wang, Zekun Luo, Zhenye Gan, Zhongyi Sun, Mingmin Chi, Chengjie Wang, Pei Wang
Domain Adaptation Active Learning Margin Classifier Active Domain Adaptation

March 1, 2022

Embodied Active Domain Adaptation for Semantic Segmentation via Informative Path Planning
René Zurbrügg, Hermann Blum, Cesar Cadena, Roland Siegwart, Lukas Schmid
Semantic Segmentation Semantic Segmentation Network Real World Environment Informative Path Planning Autonomous Operation Active Domain Adaptation Embodied Vision

February 14, 2022

D2ADA: Dynamic Density-aware Active Domain Adaptation for Semantic Segmentation
Tsung-Han Wu, Yi-Syuan Liou, Shao-Ji Yuan, Hsin-Ying Lee, Tung-I Chen, Kuan-Chih Huang, Winston H. Hsu
Semantic Segmentation Domain Adaptation Active Learning Active Domain Adaptation

December 2, 2021

Active Learning for Domain Adaptation: An Energy-Based Approach
Binhui Xie, Longhui Yuan, Shuang Li, Chi Harold Liu, Xinjing Cheng, Guoren Wang
Domain Adaptation Active Learning Unsupervised Domain Adaptation Energy Based Model Target Domain Domain Gap Active Domain Adaptation