AI Paper Atlas

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

GCA: Geometry-aware Conditional Alignment for Partial Domain Adaptation with Coding Rate Reduction

Xiaohui Chen, Chuan-Xian Ren

AAAI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 0 citations (OpenAlex)

Read the paper

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 orthogonal discriminability loss LOrt (ablation)GCA task loss · VisDA-2017 S→Raccuracy: 45.3 -> 92.0Improved
add conditional alignment loss LCA (ablation)GCA task loss · VisDA-2017 S→Raccuracy: 45.3 -> 82.7Improved
add LCA to LOrt (full model) (ablation)GCA · VisDA-2017 S→Raccuracy: 92.0 -> 93.5Improved
add LOrt to LCA (full model) (ablation)GCA · Office-31 W→Aaccuracy: 95.3 -> 96.4Improved
add LOrt and LCA (ablation)GCA · ImageCLEF I→Paccuracy: 78.3 -> 88.1Improved
add LOrt only (ablation)GCA task loss · ImageCLEF I→Paccuracy: 78.3 -> 80.3Improved
vary lambda1 and lambda2 in {2e-2..1e-1} (ablation)GCA · Office-31 W→Aaccuracy: avg 96.1, std 0.18, min 95.8, max 96.4No clear effect
use GCA instead of ARAR · VisDA-2017 S→Raccuracy: 88.7 -> 93.5Improved
use GCA instead of AGANAGAN · Office-31 avgaccuracy: 97.2 -> 98.2Improved
use GCA instead of GATE/LEAD (geometry-based)LEAD · Office-Home avgaccuracy: 73.8 -> 77.6Improved
use GCA on D→W and D→AAGAN/ETN · Office-31 D→Waccuracy: 100 -> 99.9No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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