Research map / Detection and segmentation / Open-set and few-shot detection
An Extensible Multi-modal Multi-task Object Dataset with Materials
Trevor Scott Standley, Ruohan Gao, Dawn Chen, Jiajun Wu, Silvio Savarese
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 |
|---|---|---|---|
| Train on data with missing attributes filled using generation-1 predictions | Single Image models · EMMa test set | F1 (Materials): 60.9 -> 72.7 | Improved |
| Train on data with missing attributes filled using generation-1 predictions | Text models · EMMa test set | MnRE (Price): 0.710 -> 0.704 | Hurt |
| Train on data with missing attributes filled using generation-1 predictions | Everything models · EMMa test set | F1 (Materials): 80.0 -> 86.0 | Improved |
| Use images, text, and other available attributes instead of images alone | Everything model · EMMa test set | MnRE (Mass): 0.649 -> 0.788 | Improved |
| Use images, text, and other available attributes instead of text alone | Everything model · EMMa test set | Accuracy (Category): 91.9 -> 92.2 | Improved |
| Use the proposed image model rather than Image2Mass | Mass prediction · Image2Mass Amazon test set | MnRE (Mass): 0.672 -> 0.709 | Improved |
Closest papers by meaning
- Hierarchical Material Recognition from Local Appearance (ICCV 2025 · similarity 0.85)
- Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-Modal Pretraining (ICCV 2021 · similarity 0.85)
- PROCAT: Product Catalogue Dataset for Implicit Clustering, Permutation Learning and Structure Prediction (NeurIPS 2021 · similarity 0.84)
- Task Me Anything (NeurIPS 2024 · similarity 0.84)
- 3DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition (NeurIPS 2024 · similarity 0.82)
- Multi-View Multi-Label Classification via View-Label Matching Selection (AAAI 2025 · 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.
