Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Large-Scale Distance Metric Learning With Uncertainty
Read the paperCheck 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 latent examples rather than original examples as 3-NN reference points (ablation) | MaPML · CIFAR-10 | error rate (%): 13.59±0.14 -> 12.64±0.16 | Helped |
| use latent examples rather than original examples as 3-NN reference points (ablation) | MaPML · CIFAR-100 | error rate (%): 40.49±0.15 -> 34.70±0.16 | Helped |
| use latent examples rather than original examples as 3-NN reference points (ablation) | MaPML · ImageNet ILSVRC 2012 | test error (%): 35.59±0.03 -> 33.92±0.09 | Helped |
| use latent examples rather than original examples as 3-NN reference points (ablation) | MaPML · ImageNet ILSVRC 2012 | prediction time per image: 0.15s -> 0.007s | Helped |
| learn the metric from latent examples instead of noisy original examples | MaPML · MNIST with increasing Gaussian noise | 3-NN accuracy | Helped |
| increase the latent-example ratio from 5% to 25% (ablation) | MaPML · MNIST | 3-NN accuracy | Mixed |
Closest papers by meaning
- Unsupervised Metric Learning with Synthetic Examples (AAAI 2020 · similarity 0.88)
- Denoising Multi-Similarity Formulation: A Self-Paced Curriculum-Driven Approach for Robust Metric Learning (AAAI 2023 · similarity 0.87)
- Bilevel Distance Metric Learning for Robust Image Recognition (NeurIPS 2018 · similarity 0.87)
- Efficient Stochastic Optimization for Low-Rank Distance Metric Learning (AAAI 2017 · similarity 0.87)
- Threshold-Consistent Margin Loss for Open-World Deep Metric Learning (ICLR 2024 · similarity 0.85)
- Towards Improved Proxy-Based Deep Metric Learning via Data-Augmented Domain Adaptation (AAAI 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.