AI Paper Atlas

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

Bridging Domains through Subspace-Aware Model Merging

Levy Chaves, Chao Zhou, Rebekka Burkholz, Eduardo Valle, Sandra Avila

CVPR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 0 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
trim off-diagonal outliers while keeping diagonal, versus diagonal only (ablation)SCORE · DG 8 datasets avg, ViT-B-32accuracy (%): 63.62 -> 65.69 (+2.07)Improved
trim off-diagonal outliers while keeping diagonal, versus diagonal only (ablation)SCORE · DG 8 datasets avg, ViT-B-16accuracy (%): 67.38 -> 69.97 (+2.59)Improved
trim off-diagonal outliers while keeping diagonal, versus diagonal only (ablation)SCORE · DG 8 datasets avg, ViT-L-14accuracy (%): 71.50 -> 73.04 (+1.53)Improved
add trimming to the full matrix (instead of keeping all off-diagonal entries) (ablation)SCORE · DG 8 datasets avg, ViT-B-32accuracy (%): 7.59 -> 65.69Improved
add off-diagonal components to the diagonal (trimmed) rather than off-diagonal only (ablation)SCORE · DG 8 datasets avg, ViT-B-32accuracy (%): 58.41 -> 65.69Improved
keep only off-diagonal instead of only diagonal (ablation)SCORE · DG 8 datasets avg, ViT-B-32accuracy (%): 63.62 -> 58.41 (-5.21)Hurt
replace logit ensemble with SCORE mergingfine-tuned CLIP models · DG 8 datasets avg, ViT-B-32accuracy (%): 64.57 -> 65.69 (+1.12)Improved
replace logit ensemble with SCORE mergingfine-tuned CLIP models · DG 8 datasets avg, ViT-B-16accuracy (%): 68.07 -> 69.97 (+1.90)Improved
replace logit ensemble with SCORE mergingfine-tuned CLIP models · DG 8 datasets avg, ViT-L-14accuracy (%): 71.81 -> 73.04 (+1.24)Improved
merge with Task Arithmetic instead of using zero-shot modelCLIP ViT-B-32 · DG 8 datasets avgaccuracy (%): 55.63 -> 42.47Hurt
merge with SCORE instead of using zero-shot modelCLIP ViT-B-32 · DG 8 datasets avgaccuracy (%): 55.63 -> 65.69Improved
use SCORE instead of TSV in multi-task mergingCLIP ViT-L-14 · Multi-task learning, 8 tasks avgaccuracy (%): 90.53 -> 91.17Improved

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