AI Paper Atlas

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

Mining on Heterogeneous Manifolds for Zero-Shot Cross-Modal Image Retrieval

Fan Yang, Zheng Wang, Jing Xiao, Shin'ichi Satoh

AAAI 2020 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 36 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
build graph on single-modal (heterogeneous) manifolds instead of cross-modal (homogeneous) space (ablation)Bi-directional random walk · RegDBmAP: 29.3% -> 32.1%Improved
build graph on single-modal (heterogeneous) manifolds instead of cross-modal (homogeneous) space (ablation)Bi-directional random walk · SYSU-MM01mAP: 34.9% -> 38.0%Improved
build graph on single-modal (heterogeneous) manifolds instead of cross-modal space (ablation)Bi-directional random walk · MNIST->SVHN digits 7-9mAP: 51.7% -> 60.3%Improved
build graph on single-modal (heterogeneous) manifolds instead of cross-modal space (ablation)Bi-directional random walk · SVHN->MNIST digits 7-9mAP: 52.0% -> 58.4%Improved
build graph on single-modal (heterogeneous) manifolds instead of cross-modal space (ablation)Bi-directional random walk · RegDBRank-10: 53.1% -> 47.0%Hurt
build graph on single-modal (heterogeneous) manifolds instead of cross-modal space (ablation)Bi-directional random walk · MNIST->SVHN digits 7-9Rank-10: 96.4% -> 92.2%Hurt
add heterogeneous bi-directional random walk on top of k-NN baselineResNet50 two-stream model · RegDBmAP: 23.9% -> 32.1%Improved
add heterogeneous bi-directional random walk on top of k-NN baselineResNet50 two-stream model · SYSU-MM01mAP: 26.7% -> 38.0%Improved
add heterogeneous bi-directional random walk on top of k-NN baselineResNet50 two-stream model · RegDBRank-10: 44.4% -> 47.0%Mixed
normalize similarity scores per query before ensembling both directions (ablation)Bi-directional random walk · SVHN->MNIST digits 7-9mAPNo clear effect
combine both search directions (0<lambda<1) instead of one direction only (ablation)Bi-directional random walk · SVHN->MNIST digits 7-9mAPImproved

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