Spot and Learn: A Maximum-Entropy Patch Sampler for Few-Shot Image Classification.
Wen-Hsuan ChuYu-Jhe LiJing-Cheng ChangYu-Chiang Frank WangPublished in: CVPR (2019)
Keyphrases
- description logics
- maximum entropy
- image classification
- visual features
- maximum entropy principle
- random fields
- markov models
- feature extraction
- iterative scaling
- minimum cross entropy
- principle of maximum entropy
- maximum entropy model
- transformation based learning
- image features
- multi label
- class conditional
- markov chain
- image patches
- conditional random fields
- class specific
- generative model
- video sequences