Research map / Detection and segmentation / Open-set and few-shot detection
One-sample Guided Object Representation Disassembling
Zunlei Feng, Yongming He, Xinchao Wang, Xin Gao, Jie Lei, Cheng Jin, Mingli Song
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 the augmented one-sample supervision module (ablation) | One-GORD · SVHN | AMS: 11.58 -> 5.91 | Improved |
| Add the augmented one-sample supervision module (ablation) | One-GORD · CIFAR-10 | AMS: 12.43 -> 8.43 | Improved |
| Add fuzzy classification loss (ablation) | One-GORD · SVHN | AMS: 17.01 -> 5.91 | Improved |
| Add fuzzy classification loss (ablation) | One-GORD · CIFAR-10 | AIS: 9.37 -> 5.21 | Improved |
| Add object reconstruction loss (ablation) | One-GORD · SVHN | AMS: 13.30 -> 5.91 | Improved |
| Add object reconstruction loss (ablation) | One-GORD · SVHN | AIS: 2.45 -> 2.05 | Hurt |
| Add augmented one-sample supervision (ablation) | One-GORD · CIFAR-10 | classification C-P: 39.61 -> 46.23 | Improved |
| Add fuzzy classification loss (ablation) | One-GORD · SVHN | classification C-P: 57.76 -> 60.94 | Improved |
| Use One-GORD instead of S-AE (object label supervision only) | One-GORD · SVHN | AIS: 6.51 -> 2.05 | Improved |
| Use One-GORD instead of S-AE | One-GORD · SVHN | overall precision: 57.27 -> 61.47 | Improved |
| Use One-GORD instead of MONet | One-GORD · CIFAR-10 | AIS: 11.96 -> 5.21 | Improved |
| Use One-GORD instead of DSD | One-GORD · CIFAR-10 | AMS: 14.97 -> 8.43 | Improved |
Closest papers by meaning
- One-bit Supervision for Image Classification (NeurIPS 2020 · similarity 0.85)
- Unsupervised Part-Based Disentangling of Object Shape and Appearance (CVPR 2019 · similarity 0.84)
- Object Detection with a Unified Label Space from Multiple Datasets (ECCV 2020 · similarity 0.84)
- Unsupervised Object-Level Representation Learning from Scene Images (NeurIPS 2021 · similarity 0.83)
- Doomed to Re-Annotate, Forever: The ImageNet Story (NeurIPS 2026 · similarity 0.83)
- ORIDa: Object-centric Real-world Image Composition Dataset (CVPR 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.
