AI Paper Atlas

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

Gradual Domain Adaptation: Theory and Algorithms

Yifei He, Haoxiang Wang, Bo Li, Han Zhao

JMLR 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 13 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 generated intermediate domains (4 per pair) to GSTgradual self-training · Rotated MNIST (2 given domains)accuracy (%): 61.6 -> 70.3Improved
add generated intermediate domains (4 per pair) to GSTgradual self-training · Color-Shift MNIST (2 given domains)accuracy (%): 67.6 -> 90.3Improved
add generated intermediate domains (3 per pair) to GSTgradual self-training · Portraits (2 given domains)accuracy (%): 77.0 -> 79.9Improved
add generated intermediate domains (4 per pair) to GSTgradual self-training · Cover Type (2 given domains)accuracy (%): 66.9 -> 69.8Improved
add generated intermediate domains (1 per pair) with no given domainsGST · Rotated MNIST (0 given domains)accuracy (%): 50.3 -> 48.5Hurt
add generated domains (4 per pair) with no given domainsGST · Color-Shift MNIST (0 given domains)accuracy (%): 40.5 -> 79.1Improved
use GOAT instead of one-off UDA (DANN)DANN · Rotated MNISTaccuracy (%): 44.6 -> 70.3Improved
use GOAT instead of DeepJDOTDeepJDOT · Color-Shift MNISTaccuracy (%): 65.8 -> 90.3Improved
use GOAT instead of CoViCoVi · Rotated MNIST (2 given domains)accuracy (%): 64.2 -> 70.3Improved
use GOAT instead of CoViCoVi · Color-Shift MNIST (2 given domains)accuracy (%): 77.6 -> 90.3Improved
use GOAT instead of CoViCoVi · Portraits (2 given domains)accuracy (%): 79.8 -> 79.9No clear effect
add more given intermediate domains to GOAT (0 -> 4)GOAT · Rotated MNISTaccuracy (%): 47.5 -> 82.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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