Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Deep Match Kernels for Image-Set Classification
Haoliang Sun, Xiantong Zhen, Yuanjie Zheng, Gongping Yang, Yilong Yin, Shuo Li
Check 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 DMK instead of kFDA-J | YTC image-set classification · YTC | identification rate: 79.3 ± 3.6 -> 80.3 ± 4.7 | Improved |
| Use DMK instead of SMK (p = 3) | UCSD dynamic scene classification · UCSD | identification rate: 97.6 ± 2.4 -> 98.0 ± 0.9 | Improved |
| Use DMK instead of NN-J-DR | MDSD dynamic scene classification with STR protocol · MDSD-STR | identification rate: 80.2 ± 3.7 -> 81.5 ± 4.7 | Improved |
| Use DMK instead of kFDA-HL | MDSD dynamic scene classification with LOO protocol · MDSD-LOO | identification rate: 87.1 ± 5.3 -> 87.2 ± 5.0 | Improved |
| Use DMK instead of LEML | ETH-80 set-based object categorization · ETH-80 | identification rate: 96.0 ± 2.1 -> 96.8 ± 1.5 | Improved |
Closest papers by meaning
- Interferences in Match Kernels (TPAMI 2016 · similarity 0.88)
- Learning and Aggregating Deep Local Descriptors for Instance-level Recognition (ECCV 2020 · similarity 0.86)
- Image Matching from Handcrafted to Deep Features: A Survey (IJCV 2020 · similarity 0.86)
- Matching Feature Sets for Few-Shot Image Classification (CVPR 2022 · similarity 0.85)
- End-to-End Kernel Learning with Supervised Convolutional Kernel Networks (NeurIPS 2016 · similarity 0.85)
- OmniGlue: Generalizable Feature Matching with Foundation Model Guidance (CVPR 2024 · 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.
