AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Learning Robust Visual-Semantic Embeddings

Yao-Hung Hubert Tsai, Liang-Kang Huang, Ruslan Salakhutdinov

ICCV 2017 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs · 170 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 unsupervised reconstruction and MMD objectives on labeled training data (ablation)ReViSE (supervised only) · Inductive zero-shot recognition averagetop-1 accuracy (%): 3.4% recognition improvementImproved
add unsupervised reconstruction and MMD objectives on labeled training data (ablation)ReViSE (supervised only) · Inductive zero-shot retrieval averagemAP (%): 3.9% retrieval improvementImproved
add unlabeled training data to unsupervised loss (ablation)ReViSE^b · AwA+CUB inductive zero-shottop-1 accuracy (%): 2.6% recognition improvement and 0.4% retrieval improvementImproved
add unsupervised-data adaptation inference (ablation)ReViSE^c · Inductive zero-shot recognition averagetop-1 accuracy (%): 5.0% average recognition improvementImproved
add unsupervised-data adaptation inference (ablation)ReViSE^c · Inductive zero-shot retrieval averagemAP (%): 5.8% average retrieval improvementImproved
add unsupervised-data adaptation inference (ablation)ReViSE^c · Transductive zero-shot recognition averagetop-1 accuracy (%): 53.6 -> 68.1Improved
add MMD loss between visual and textual codes (ablation)ReViSE^dagger · Transductive zero-shot recognition averagetop-1 accuracy (%): 66.8 -> 68.1Improved
add contractive loss (ablation)ReViSE^dagger-dagger · Transductive zero-shot recognition averagetop-1 accuracy (%): 65.8 -> 66.8Improved
apply unsupervised-data adaptation inference to DeViSEDeViSE · Transductive zero-shot recognition averagetop-1 accuracy (%): 49.3 -> 60.6Improved
apply unsupervised-data adaptation inference to CMTCMT · Transductive zero-shot recognition averagetop-1 accuracy (%): 50.5 -> 60.5Improved
apply unlabeled-data adaptation to CMT in inductive setting on AwA test imagesCMT · AwA test images inductive zero-shot recognitiontop-1 accuracy (%): 3.1% recognition deteriorationHurt
apply unlabeled-data adaptation to DeViSE in inductive setting on AwA test imagesDeViSE · AwA test images inductive zero-shot retrievalmAP (%): 2.7% retrieval deteriorationHurt

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