Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Unsupervised Similarity Learning Using Partially Ordered Sets
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 |
|---|---|---|---|
| add poset-based similarity learning to the ImageNet-initialized method | Olympic Sports retrieval · Olympic Sports | AUC: 0.83 -> 0.85 | Helped |
| use poset-based similarity learning instead of the triplet method | Olympic Sports retrieval · Olympic Sports | AUC: 0.63 -> 0.78 | Helped |
| transfer the Olympic Sports representation to LSP without further training | zero-shot pose estimation · LSP | PCP@0.5 Total: 43.5 -> 48.3 | Helped |
| use the proposed unsupervised representation instead of Shuffle&Learn for initialization | DeepPose · LSP | PCP@0.5 Total: 49.3 -> 51.0 | Helped |
| use the proposed unsupervised representation instead of random initialization | DeepPose · LSP | PCP@0.5 Total: 42.0 -> 51.0 | Helped |
| use the proposed unsupervised representation instead of Shuffle&Learn for initialization | DeepPose · MPII Pose | PCKh@0.5 Total: 69.3 -> 72.7 | Helped |
| use the proposed unsupervised representation instead of random initialization | DeepPose · MPII Pose | PCKh@0.5 Total: 65.4 -> 72.7 | Helped |
| apply poset-based learning to the Wang et al. triplet representation | PASCAL VOC 2007 zero-shot classification · PASCAL VOC 2007 | classification performance (k=5): 0.4501 -> 0.5101 | Helped |
Closest papers by meaning
- Unsupervised Feature Learning via Non-Parametric Instance Discrimination (CVPR 2018 · similarity 0.88)
- Un-mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning (AAAI 2022 · similarity 0.87)
- Unsupervised Deep Learning by Neighbourhood Discovery (ICML 2019 · similarity 0.87)
- Relative Order Analysis and Optimization for Unsupervised Deep Metric Learning (CVPR 2021 · similarity 0.87)
- CliqueCNN: Deep Unsupervised Exemplar Learning (NeurIPS 2016 · similarity 0.86)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.85)
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.