AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-Commerce

Yang Jin, Yongzhi Li, Zehuan Yuan, Yadong Mu

CVPR 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Vision-language pretraining · 12 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
Use ECLIP instance-centric pretraining instead of global image-text pretrainingECLIP · M5Product zero-shot classificationAcc@1: 39.3 -> 44.8Improved
Use ECLIP instance-centric pretraining instead of global image-text pretrainingECLIP · Fine-grained product retrievalR@1: 35.6 -> 45.0Improved
Add inter-product multi-modal learning (ablation)ECLIP · Coarse-level product retrievalmAP@1 (%): 61.6 -> 64.4Improved
Add intra-product multi-modal learning (ablation)ECLIP · Coarse-level product retrievalmAP@1 (%): 61.6 -> 62.2Improved
Combine inter-product and intra-product learning (ablation)ECLIP · Coarse-level product retrievalmAP@1 (%): 64.4 -> 65.2Improved
Use random negative queries instead of negative text prompts or EMA-updated queries (ablation)ECLIP · Instance-level product retrievalmAP@10: 84.9; 85.1; 86.8Mixed
Increase instance query count from 20 to 40 (ablation)ECLIP · Instance-level product retrieval (visual modality)mAP@10: 89.6 -> 89.9Improved
Replace cross-attention with slot-attention (ablation)ECLIP decoder · Visual groundingAcc@0.7: 66.3 -> 70.5Improved
Add instance-text matching loss (ablation)ECLIP · Visual groundingAcc@0.7: 69.6 -> 70.0Improved
Add entropy regularization (ablation)ECLIP with instance-text matching loss · Visual groundingAcc@0.7: 70.0 -> 70.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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