AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation

Hongbin Lin, Yifan Zhang, Zhen Qiu, Shuaicheng Niu, Chuang Gan, Yanxia Liu, Mingkui Tan

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 59 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add L_ce on pseudo-labeled target data (ablation)backbone · Office-31-CIFinal accuracy: 77.5 -> 79.4Improved
add prototype knowledge replay loss L_dis (ablation)ProCA (L_ce) · Office-31-CIFinal accuracy: 79.4 -> 81.2Improved
add prototype knowledge replay loss L_dis (ablation)ProCA (L_ce) · Office-31-CIFinal S-1 accuracy: 86.8 -> 89.0Improved
add prototype contrastive alignment L_con (ablation)ProCA (L_ce) · Office-31-CIFinal accuracy: 79.4 -> 80.8Improved
add prototype contrastive alignment L_con (ablation)ProCA (L_ce) · Office-31-CIFinal S-1 accuracy: 86.8 -> 88.0Improved
add L_con on top of L_ce and L_dis (ablation)ProCA · Office-31-CIFinal accuracy: 81.2 -> 82.1Improved
add L_dis on top of L_ce and L_con (ablation)ProCA · Office-31-CIFinal accuracy: 80.8 -> 82.1Improved
add L_con on top of L_ce and L_dis (ablation)ProCA · Office-31-CIFinal S-1 accuracy: 89.0 -> 90.8Improved
add label prototype identification (ablation)PADA · Office-31-CIFinal accuracy: 57.4 -> 73.0Improved
add label prototype identification (ablation)PADA · Office-31-CIFinal S-1 accuracy: 48.3 -> 80.4Improved
add label prototype identification (ablation)BA3US · Office-31-CIFinal accuracy: 78.3 -> 80.4Improved
add label prototype identification (ablation)BA3US · Office-31-CIFinal S-1 accuracy: 88.7 -> 89.8Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy