Spot and Learn: A Maximum-Entropy Patch Sampler for Few-Shot Image Classification

By Wen-Hsuan Chu, Yu-Jhe Li, Jing-Cheng Chang, Yu-Chiang Frank Wang. 2019

67 citations recorded by the source corpus.

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 de-correlates 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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Chunhua Shen
2. Guosheng Lin
3. Chi Zhang
4. Shiji Song
5. Gao Huang
6. Yulin Wang
7. Qixiang Ye
8. Jianbin Jiao

In Computer Vision and Pattern Recognition

1. Chunhua Shen
2. Guosheng Lin
3. Luc Van Gool
4. Dacheng Tao
5. Shiji Song
6. Qixiang Ye
7. Yi Yang
8. Chi Zhang

In Radiology, Nuclear Medicine and Imaging

1. Chi Zhang
2. Guosheng Lin
3. Yisheng Song
4. Chunhua Shen

Citations in the corpus

• Incremental Few-Shot Object Detection (2020, neutral): “Note that there are many more recent FSL methods [6, 26, 7, 17, 47, 55, 50, 27, 39, 11, 16] that produce better performance on image classification tasks than MAML.”
• Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation (2021, background): “While meta-learning [36, 27, 8, 15, 44, 38, 21] contributed important optimization methods and data augmentation [13, 35] aggregated performance, metric learning [32, 30, 11, 5] with prototype models [23, 4, 6, 41, 40, 18] represent the majority of few-shot learning approaches.”
• A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities (2022, methodology): “1 A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities Yisheng Song, Ting Wang∗, Subrota K Mondal, Jyoti Prakash Sahoo Abstract—Few-shot learning (FSL) has emerged as an effective learning method and shows great potential.”
• Self-Supervised Learning for Few-Shot Image Classification (2019, unknown): “…4 Conv 49.97 ± 0.32% 65.99 ± 0.58% ProtoNet [5] 4 Conv 49.42 ± 0.78% 68.20 ± 0.66% Baseline* [28] 4 Conv 41.08 ± 0.70% 54.50% ± 0.66 Spot&learn [29] 4 Conv 51.03 ± 0.78% 67.96% ± 0.71 DN4 [30] 4 Conv 51.24 ± 0.74% 71.02% ± 0.64 SNAIL [31] ResNet12 55.71 ± 0.99% 68.88 ± 0.92% ProtoNet + [5]…”
• DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover’s Distance and Structured Classifiers (2020, unknown): “Apart from the two popular branches, many other promising methods are also proposed to handle the few-shot classification problem, such as works based on graph theories [13, 15, 21], reinforcement learning [6], differentiable”
• DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning (2020, background): “classification problem, such as works based on graph theories [66], [67], [68], [69], reinforcement learning [70], differentiable SVM [71], generative models [72], [73], [74], [75], [76], [77], [78], [79], [80], transductive learning [81], [82], [83], [84], [85], recurrent models [86], [87], self-su”
• Adaptive Focus for Efficient Video Recognition (2021, background): “networks (CNNs) are able to produce correct predictions with only a few discriminative regions of the whole image [45, 53, 18, 35, 14, 5].”
• Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification (2020, background): “In fact, CNNs are shown to be able to produce correct classification results with only a few class-discriminative patches, such as the head of a dog or the wings of a bird [38, 12, 8].”