Research map / Label-efficient and robust learning / Domain adaptation and generalization
DATE: Domain Adaptive Product Seeker for E-Commerce
Haoyuan Li, Hao Jiang, Tao Jin, Mengyan Li, Yan Chen, Zhijie Lin, Yang Zhao, Zhou Zhao
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 |
|---|---|---|---|
| Use DATE rather than ViLT for image retrieval | Product retrieval · TMPS | R@1: 14.39 -> 16.32 | Improved |
| Use DATE rather than ViLT for image retrieval | Product retrieval · TMPS | R@50: 83.23 -> 82.58 | Hurt |
| Use DATE rather than ViLT for image retrieval | Product retrieval · TLPS | R@1: 5.38 -> 6.44 | Improved |
| Use DATE rather than TransVG | Product grounding · TMPS | mIoU: 84.52 -> 86.67 | Improved |
| Use DATE rather than TransVG | Product grounding · TLPS | Pr@1: 77.93 -> 81.43 | Improved |
| Use DATE rather than pseudo-label training | Unsupervised PG-DA · L→M (TLPS→TMPS) | mIoU: 77.02 -> 79.92 | Improved |
| Use DATE rather than pseudo-label training | Unsupervised PG-DA · M→L (TMPS→TLPS) | Pr@1: 71.48 -> 74.75 | Improved |
| Add [REP] semantics aggregation instead of average pooling (ablation) | DATE cooperative seekers · TMPS | mIoU: 83.11 -> 86.67 | Improved |
| Add the object-seeking transformer instead of using an MLP for fusion (ablation) | DATE cooperative seekers · TMPS | mIoU: 82.25 -> 86.67 | Improved |
| Add [REP] aggregation and the object-seeking transformer (ablation) | DATE cooperative seekers · TMPS | mIoU: 80.45 -> 86.67 | Improved |
| Add [REP] semantics aggregation instead of average pooling (ablation) | DATE cooperative seekers · TLPS | mIoU: 67.31 -> 70.24 | Improved |
| Add the object-seeking transformer instead of using an MLP for fusion (ablation) | DATE cooperative seekers · TLPS | mIoU: 65.82 -> 70.24 | Improved |
Later papers that compared with this method
1 later accepted paper reports DATE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Agile Multi-Source-Free Domain Adaptation (AAAI 2024 · better on 2 of 2 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
- TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval (NeurIPS 2026 · similarity 0.85)
- Cross-Domain Product Representation Learning for Rich-Content E-Commerce (ICCV 2023 · similarity 0.85)
- Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-Modal Pretraining (ICCV 2021 · similarity 0.85)
- Multi-Domain Deep Learning from a Multi-View Perspective for Cross-Border E-commerce Search (AAAI 2024 · similarity 0.83)
- Transformer-Empowered Multi-Modal Item Embedding for Enhanced Image Search in E-commerce (AAAI 2024 · similarity 0.83)
- eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data (ICML 2024 · similarity 0.82)
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.
