Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Expected Hitting Time Distance
De-Chuan Zhan, Peng Hu, Zui Chu, Zhi-Hua Zhou
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 |
|---|---|---|---|
| Use LED learned EHT distance instead of Euclidean k-NN | LED · CalTech101-BOW | accuracy: .153±.005 -> .448±.022 | Improved |
| Use LED instead of Euclidean k-NN | LED · CalTech101-SPM | accuracy: .501±.009 -> .732±.005 | Improved |
| Use LED instead of ITML | LED · CalTech101-SPM | accuracy: .688±.009 -> .732±.005 | Improved |
| Use LED instead of ITML | LED · ImageNet-HOG | accuracy: .242±.008 -> .322±.006 | Improved |
| Use LED instead of best baseline PLML | LED · VOC2009-BOW | accuracy: .627±.009 -> .629±.011 | Improved |
| Use LED instead of LDML | LED · Reuters-TF | accuracy: .944± .004 -> .946±.003 | Improved |
| Use LED instead of ITML | LED · 20NewsGroups-TF | accuracy: .663±.034 -> .671±.007 | Improved |
| Use LED instead of Euclidean k-NN | LED · ImageNet-HOG | accuracy: .315±.005 -> .322±.006 | Improved |
| Use stochastic gradient LED-SGD instead of full LED | LED · ImageNet-HOG | accuracy: .322±.006 -> .325±.005 | Improved |
| Use stochastic gradient LED-SGD instead of full LED | LED · Reuters-TF | accuracy: .946±.003 -> .940±.004 | Hurt |
| Use stochastic gradient LED-SGD instead of full LED | LED · CalTech101-SPM | accuracy: .732±.005 -> .731±.008 | No clear effect |
| Use DNE instead of Euclidean k-NN on ImageNet-HOG | baseline · ImageNet-HOG | accuracy: .315±.005 -> .071±.060 | Hurt |
Closest papers by meaning
- Learning Distance for Sequences by Learning a Ground Metric (ICML 2019 · similarity 0.84)
- Large-Scale Distance Metric Learning With Uncertainty (CVPR 2018 · similarity 0.83)
- Learning Distances from Data with Normalizing Flows and Score Matching (ICML 2025 · similarity 0.82)
- Curvilinear Distance Metric Learning (NeurIPS 2019 · similarity 0.82)
- Hierarchical Integral Probability Metrics: A distance on random probability measures with low sample complexity (ICML 2024 · similarity 0.82)
- Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making (ICML 2024 · similarity 0.81)
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.
