AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

ZeroDiff++: Generative Test-Time Adaptation for Zero-shot Learning

Zihan Ye, Shreyank N Gowda, Kaile Du, Weijian Luo, Ling Shao

TPAMI 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 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
add diffusion augmentation to the f-VAEGAN baseline (ablation)ZeroDiff++ · AWA2 ZSLtop-1 accuracy: 76.0 -> 80.0Improved
add SC representations and mutual learning loss on top of diffusion augmentation (ablation)ZeroDiff++ · AWA2 ZSLtop-1 accuracy: 80.0 -> 86.4Improved
add DiffTTA to the model with DiffAug, SC and L_mu (ablation)ZeroDiff++ · AWA2 GZSLharmonic mean H: 76.9 -> 78.7Improved
add DiffGen to the model with DiffAug, SC and L_mu (ablation)ZeroDiff++ · AWA2 GZSLharmonic mean H: 76.9 -> 84.4Improved
add DiffTTA when DiffGen is used (ablation)ZeroDiff++ · AWA2 GZSLharmonic mean H: 88.0 -> 92.3Improved
add DiffTTA when generating with fully-noised FNGen (ablation)ZeroDiff++ · AWA2 GZSLharmonic mean H: 73.8 -> 73.3No clear effect
replace FNGen inference with DiffGen (ablation)ZeroDiff++ · AWA2 GZSLharmonic mean H: 73.8 -> 88.0Improved
replace DiffusionZSL reconstruction-error inference with DiffGen (ablation)ZeroDiff++ · AWA2 GZSLharmonic mean H: 11.9 -> 88.0Improved
use real paired SC representation instead of generated SC in DiffGen (ablation)DiffGen · AWA2 GZSLharmonic mean H: 81.8 -> 91.9Improved
use intermediate diffusion time t=2 rather than extreme t in DiffGen with real SC (ablation)DiffGen · AWA2 GZSLharmonic mean H: 91.4 -> 91.9Improved
randomize diffusion time t in DiffGen instead of fixing it (ablation)DiffGen · AWA2 GZSLharmonic mean H: 91.9 -> 91.6No clear effect
add contrastive representation to the final classifier input (V+C) (ablation)ZeroDiff++ · AWA2 GZSLharmonic mean H: 90.6 -> 92.3Improved

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