AI Paper Atlas

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

TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation

Haoang Chi, Feng Liu, Wenjing Yang, Long Lan, Tongliang Liu, Bo Han, William Cheung, James Kwok

NeurIPS 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 2 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
One-step joint training instead of two-step ST+F (ablation)TOHAN · digits average, 1 target per classaccuracy (%): 61.8 -> 63.3Improved
One-step joint training instead of two-step ST+F (ablation)TOHAN · digits average, 7 target per classaccuracy (%): 68.4 -> 70.0Improved
Use both source and target generator losses instead of source only (S+F) (ablation)TOHAN · digits average, 7 target per classaccuracy (%): 67.2 -> 70.0Improved
Use both generator losses instead of target only (T+F) (ablation)TOHAN · digits average, 7 target per classaccuracy (%): 67.4 -> 70.0Improved
TOHAN vs SHOTTOHAN · U->S, 1 target per classaccuracy (%): 30.3 -> 29.9Hurt
TOHAN vs SHOTTOHAN · U->M, 2 target per classaccuracy (%): 85.5 -> 85.2Hurt
TOHAN vs fine-tuningTOHAN · M->S, 7 target per classaccuracy (%): 28.3 -> 33.2Improved
TOHAN vs without adaptationTOHAN · SL->CFaccuracy (%): 51.8 -> 56.6Improved
TOHAN vs S+FTOHAN · SL->CFaccuracy (%): 56.9 -> 56.6Hurt
TOHAN vs without adaptationTOHAN · CF->SLaccuracy (%): 70.6 -> 72.8Improved
Increase target data per class from 1 to 7TOHAN · M->Saccuracy (%): 26.7 -> 33.2Improved

Later papers that compared with this method

1 later accepted paper reports TOHAN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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