AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Cross-Domain Product Representation Learning for Rich-Content E-Commerce

Xuehan Bai, Yan Li, Yanhua Cheng, Wenjie Yang, Quan Chen, Han Li

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 6 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 to the contrastive cross-domain loss (ablation)COPE · ROPE P2V retrievalR@1: 51.88 -> 82.58Improved
add classification loss (ablation)COPE · ROPE L2P retrievalR@1: 23.11 -> 42.33Improved
use product-balance sampling instead of random sampling (ablation)COPE · ROPE P2V retrievalR@1: 70.08 -> 82.58Improved
use product-balance sampling instead of random sampling (ablation)COPE · ROPE L2P retrievalR@1: 33.10 -> 42.33Improved
train COPE on ROPE instead of using general or product-page-only vision-language modelscross-domain product retrieval · ROPE P2L retrievalR@1: 34.37 -> 54.06 (vs ChineseCLIP)Improved
transfer COPE to Product1M without fine-tuningCOPE · Product1MmAP@10: 79.36 -> 86.02Improved
transfer COPE to Product1M without fine-tuningCOPE · Product1MPrec@100: 73.86 -> 66.58Hurt
exclude ASR texts and text modules for video and live domainsCOPE · ROPEdesign choiceImproved

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