Research map / Detection and segmentation / Open-set and few-shot detection
Symmetry and Group in Attribute-Object Compositions
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 symmetry-based coupling and decoupling with RMD recognition | SymNet · MIT-States unseen compositions | Top-1 accuracy: +2.1% | Helped |
| Use symmetry-based coupling and decoupling with RMD recognition | SymNet · UT-Zappos unseen compositions | Top-1 accuracy: +3.8% | Helped |
| Add symmetry loss (ablation) | SymNet · MIT-States unseen compositions | Top-1 accuracy: 18.3 -> 19.9 | Helped |
| Add group-axiom losses (ablation) | SymNet · MIT-States unseen compositions | Top-1 accuracy: 16.9 -> 19.9 | Helped |
| Add invertibility loss (ablation) | SymNet · MIT-States unseen compositions | Top-1 accuracy: 17.9 -> 19.9 | Helped |
| Add commutativity loss (ablation) | SymNet · MIT-States unseen compositions | Top-1 accuracy: 17.8 -> 19.9 | Helped |
| Add closure loss (ablation) | SymNet · MIT-States unseen compositions | Top-1 accuracy: 18.0 -> 19.9 | Helped |
| Add classification losses (ablation) | SymNet · MIT-States unseen compositions | Top-1 accuracy: 10.3 -> 19.9 | Helped |
| Add triplet loss (ablation) | SymNet · MIT-States unseen compositions | Top-1 accuracy: 17.8 -> 19.9 | Helped |
| Add attribute-as-attention module (ablation) | SymNet · MIT-States unseen compositions | Top-1 accuracy: 18.0 -> 19.9 | Helped |
| Use L2 distance rather than L1 distance (ablation) | SymNet RMD · MIT-States unseen compositions | Top-1 accuracy: 7.1 -> 19.9 | Helped |
| Use L2 distance rather than cosine distance (ablation) | SymNet RMD · UT-Zappos unseen compositions | Top-1 accuracy: 18.7 -> 52.1 | Helped |
Closest papers by meaning
- MatrixNet: Learning over symmetry groups using learned group representations (NeurIPS 2024 · similarity 0.86)
- A Generative Model of Symmetry Transformations (NeurIPS 2024 · similarity 0.85)
- Learning Infinitesimal Generators of Continuous Symmetries from Data (NeurIPS 2024 · similarity 0.84)
- Learning symmetries via weight-sharing with doubly stochastic tensors (NeurIPS 2024 · similarity 0.83)
- Improving Equivariant Networks with Probabilistic Symmetry Breaking (ICLR 2025 · similarity 0.83)
- Probing Equivariance and Symmetry Breaking in Convolutional Networks (NeurIPS 2025 · similarity 0.83)
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.