Name
Abstract | ||
|---|---|---|
Few-shot learning (FSL) requires one to learn from object categories with a small amount of training data (as novel classes), while the remaining categories (as base classes) contain a sufficient amount of data for training. It is often desirable to transfer knowledge from the base classes and derive dominant features efficiently for the novel samples. In this work, we propose a sampling method that decorrelates an image based on maximum entropy reinforcement learning, and extracts varying sequences of patches on every forward-pass with discriminative information observed. This can be viewed as a form of "learned" data augmentation in the sense that we search for different sequences of patches within an image and performs classification with aggregation of the extracted features, resulting in improved FSL performances. In addition, our positive and negative sampling policies along with a newly defined reward function would favorably improve the effectiveness of our model. Our experiments on two benchmark datasets confirm the effectiveness of our framework and its superiority over recent FSL approaches. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/CVPR.2019.00641 | 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) |
Field | DocType | ISSN |
Computer vision,Pattern recognition,Computer science,Artificial intelligence,Principle of maximum entropy,Contextual image classification | Conference | 1063-6919 |
Citations | PageRank | References |
4 | 0.38 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wen-Hsuan Chu | 1 | 4 | 0.72 |
| Yu-Jhe Li | 2 | 4 | 1.05 |
| Jing-Cheng Chang | 3 | 6 | 0.74 |
| Yu-Chiang Frank Wang | 4 | 914 | 61.63 |