AI Paper Atlas

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

Improving Zero-Shot Generalization for CLIP with Variational Adapter

Ziqian Lu, Fengli Shen, Mushui Liu, Yunlong Yu, Xi Li

ECCV 2024 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 7 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 classification loss Lcls to Ldis (ablation)PVA · CUB GZSLharmonic mean H: 22.5 -> 66.1Improved
add cross-domain reconstruction loss Lcr (ablation)PVA · AwA2 GZSLharmonic mean H: 86.6 -> 90.3Improved
add refinement with CLIP global features (residual, epsilon 0.9) (ablation)PVA · CUB GZSLharmonic mean H: 69.6 -> 71.4Improved
add refinement with CLIP global features (ablation)PVA · AwA2 GZSLharmonic mean H: 90.3 -> 90.7No clear effect
replace variational adapter with MLP adapter plus data separation (ablation)PVA · AwA2 GZSLharmonic mean H: 90.7 -> 79.1Hurt
add data separation to MLP adapter (ablation)MLP adapter · AwA2 GZSLharmonic mean H: 85.0 -> 79.1Hurt
add data separation to MLP adapter (ablation)MLP adapter · CUB GZSLharmonic mean H: 57.0 -> 66.6Improved
replace Ldis-only domain detector with full losses (ablation)PVA domain detection · CUBFPR at 95% TPR: 77.1 -> 2.6Improved
use CLIP features in generative method TF-VAEGANTF-VAEGAN · AwA2 GZSLharmonic mean HNo clear effect
increase threshold ratio tau to 0.99 or above (ablation)PVA · AwA2 GZSLnovel-class accuracy NHurt
fine-tune CLIP with CoOP prompt learningCLIP · AwA2 GZSLnovel-class accuracy N: 86.6 -> 72.7Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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