AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Multi-Hypothesis Test-Time Adaptation to Mitigate Underspecification

Afshar Shamsi, Xiao-Yu Guo, Hamid Alinejad-Rokny, Arash Mohammadi, Damien Teney, Ehsan Abbasnejad

ECCV 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 1 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 gradient diversificationnaive ensemble of 3 particles · ImageNet-C batch size 1 (ViTBase-LN)accuracy: 62.17 -> 63.14Improved
use three particles instead of DeYO's single model (ablation)DeYO · ImageNet-C batch size 1 (ViTBase-LN)accuracy: 60.57 -> 62.17Improved
add gradient diversification to DeYO-style baselineDeYO · ImageNet-C batch size 1 (ResNet-50-GN)accuracy: 44.40 -> 46.90Improved
add gradient diversificationDeYO · ImageNet-C label shifts (ViTBase-LN)accuracy: 62.37 -> 63.36Improved
add gradient diversificationDeYO · ImageNet-C mixed shifts (ViTBase-LN)top-1 accuracy: 57.05 -> 61.36Improved
add gradient diversificationDeYO · ImageNet-C mixed shifts (ResNet-50-GN)top-1 accuracy: 31.36 -> 34.36Mixed
add flip augmentation (input diversification) to gradient diversification (ablation)Grad diversification · ImageNet-C batch size 1 (ViTBase-LN)accuracy: 63.08 -> 64.72Improved
add flip augmentation to naive ensemble (ablation)Naive ensemble · ImageNet-C batch size 1 (ViTBase-LN)accuracy: 61.88 -> 62.26Improved
use different optimizers per particle plus Grad regularizer (ablation)Grad diversification · ImageNet-C batch size 1 (ViTBase-LN)accuracy: 63.14 -> 63.08No clear effect
add gradient diversification to TentTent · ImageNet-C batch size 1 (7 corruptions)accuracy: 51.52 -> 53.63Improved
increase particles from N=1 to N=3 (ablation)Grad diversification · ImageNet-C Gaussian noiseaccuracyImproved
dot-product gradient diversity instead of cosine or L2 difference (ablation)Grad diversification · ImageNet-C zoom bluraccuracyImproved

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