Region Comparison Network for Interpretable Few-shot Image Classification

8 Sep 2020  ·  Zhiyu Xue, Lixin Duan, Wen Li, Lin Chen, Jiebo Luo ·

While deep learning has been successfully applied to many real-world computer vision tasks, training robust classifiers usually requires a large amount of well-labeled data. However, the annotation is often expensive and time-consuming. Few-shot image classification has thus been proposed to effectively use only a limited number of labeled examples to train models for new classes. Recent works based on transferable metric learning methods have achieved promising classification performance through learning the similarity between the features of samples from the query and support sets. However, rare of them explicitly considers the model interpretability, which can actually be revealed during the training phase. For that, in this work, we propose a metric learning based method named Region Comparison Network (RCN), which is able to reveal how few-shot learning works as in a neural network as well as to find out specific regions that are related to each other in images coming from the query and support sets. Moreover, we also present a visualization strategy named Region Activation Mapping (RAM) to intuitively explain what our method has learned by visualizing intermediate variables in our network. We also present a new way to generalize the interpretability from the level of tasks to categories, which can also be viewed as a method to find the prototypical parts for supporting the final decision of our RCN. Extensive experiments on four benchmark datasets clearly show the effectiveness of our method over existing baselines.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) RCN - Conv4-64 Accuracy 61.61 # 36
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) RCN - ResNet12 Accuracy 69.02 # 33
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) RCN - ResNet12 Accuracy 82.96 # 33
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) RCN - Conv4-64 Accuracy 77.63 # 36
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) RCN - Conv4-64 Accuracy 53.57 # 82
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) RCN - ResNet12 Accuracy 57.40 # 73
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) RCN - ResNet12 Accuracy 75.19 # 64
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) RCN - Conv4-64 Accuracy 71.63 # 72

Methods