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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add classification loss to the contrastive cross-domain loss (ablation) | COPE · ROPE P2V retrieval | R@1: 51.88 -> 82.58 | Improved |
| add classification loss (ablation) | COPE · ROPE L2P retrieval | R@1: 23.11 -> 42.33 | Improved |
| use product-balance sampling instead of random sampling (ablation) | COPE · ROPE P2V retrieval | R@1: 70.08 -> 82.58 | Improved |
| use product-balance sampling instead of random sampling (ablation) | COPE · ROPE L2P retrieval | R@1: 33.10 -> 42.33 | Improved |
| train COPE on ROPE instead of using general or product-page-only vision-language models | cross-domain product retrieval · ROPE P2L retrieval | R@1: 34.37 -> 54.06 (vs ChineseCLIP) | Improved |
| transfer COPE to Product1M without fine-tuning | COPE · Product1M | mAP@10: 79.36 -> 86.02 | Improved |
| transfer COPE to Product1M without fine-tuning | COPE · Product1M | Prec@100: 73.86 -> 66.58 | Hurt |
| exclude ASR texts and text modules for video and live domains | COPE · ROPE | design choice | Improved |
Closest papers by meaning
- Cross-view Semantic Alignment for Livestreaming Product Recognition (ICCV 2023 · similarity 0.88)
- Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-Modal Pretraining (ICCV 2021 · similarity 0.87)
- Multi-Domain Deep Learning from a Multi-View Perspective for Cross-Border E-commerce Search (AAAI 2024 · similarity 0.82)
- TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval (NeurIPS 2026 · similarity 0.82)
- Retrieval Across Any Domains via Large-scale Pre-trained Model (ICML 2024 · similarity 0.82)
- Transformer-Empowered Multi-Modal Item Embedding for Enhanced Image Search in E-commerce (AAAI 2024 · similarity 0.81)
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.
