AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Entity-Graph Enhanced Cross-Modal Pretraining for Instance-level Product Retrieval

Xiao ming Dong, Xunlin Zhan, Yunchao Wei, Xiao-Yong Wei, Yaowei Wang, Minlong Lu, Xiaochun Cao, Xiaodan Liang

TPAMI 2023 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 14 citations (OpenAlex)

Read the paper

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 masked entity modeling (E-Masked), image-text features (ablation)EGE-CMP · Product1M multi-product retrievalmAP: 81.49 -> 85.71Improved
add masked entity modeling (E-Masked), text features (ablation)EGE-CMP · Product1M multi-product retrievalmAP: 78.23 -> 83.48Improved
add masked entity modeling (E-Masked), image features (ablation)EGE-CMP · Product1M multi-product retrievalmAP: 80.94 -> 83.28Improved
add entity node loss (ablation)EGE-CMP · Product1M multi-product retrievalmAP: 85.71 -> 85.76No clear effect
add entity subgraph loss (ablation)EGE-CMP · Product1M multi-product retrievalmAP: 85.76 -> 86.91Improved
add entity subgraph loss, text features (ablation)EGE-CMP · Product1M multi-product retrievalmAP: 83.50 -> 85.25Improved
add single-modal transformer layers (0,6,6 -> 4,4,4) (ablation)EGE-CMP · Product1M multi-product retrievalmAP@10: 50.0 -> 86.9Improved
add cross-transformer layers (6,0,6 -> 4,4,4) (ablation)EGE-CMP · Product1M multi-product retrievalmAP@10: 85.9 -> 86.9Improved
add co-transformer layers (6,6,0 -> 4,4,4) (ablation)EGE-CMP · Product1M multi-product retrievalmAP@10: 85.8 -> 86.9Improved
scale to 24 layers (8,8,8) from 12 (ablation)EGE-CMP · Product1M multi-product retrievalmAP@10: 86.9 -> 86.9No clear effect
shrink to 6 layers (2,2,2) from 12 (ablation)EGE-CMP · Product1M multi-product retrievalmAP@10: 86.9 -> 83.7Hurt
replace UNITER with EGE-CMP on unseen brandsEGE-CMP · Product1M zero-shot (20 brands)mAP@10: 43.3 -> 46.8Improved

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