CSN: Component supervised network for few-shot classification

The few-shot classification (FSC) task aims to classify data with limited labeled examples across different categories. Typically, researchers pre-train a feature extractor using base data and use it to extract features from novel data for classification Notably, the novel set only has a few annotated samples and has non-overlapped categories from the base set, which leads to the fact that the pre-trained feature extractor cannot adapt to the novel data flawlessly. We dub this problem as Feature-Extractor-Maladaptive (FEM) problem. Starting from the root cause of this problem, this paper presents a new scheme called Component Supervised Network (CSN), to improve the performance of FSC. We believe that even though the categories in the base and novel sets are different, their sample components share similarities. For example, both cats and dogs contain leg and head components. These entity components are intra-class stable and have cross-category versatility, making them useful for generalization to new categories. However, finding common information among different categories is difficult in real-world scenarios, hindering the possibility of modeling based on this assumption. To overcome this, we first design a Dictionary-based Implicit-Component Generator (DICG) to mine common information of different sets; then construct an implicit-component-based auxiliary task to improve the adaptability of the feature extractor. We evaluated our CSN on three benchmark datasets (mini-ImageNet, tiered-ImageNet, and FC100) and achieved improvements of at least 0. 9% compared to classical methods, demonstrating the efficiency of our approach.

Authors

• Rui Xu Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing, College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China Engineering Research Center of Big Data Intelligence, Ministry of Education, Fuzhou 350116, China
• Shuai Shao
• Lei Xing Xi'an Jiaotong University
• Yujun Wei
• Weifeng Liu China University of Petroleum (East China)
• Baodi Liu China University of Petroleum (East China)
• Yanjiang Wang

Keywords

• Few-shot classification (FSC)
• Feature-extractor-maladaptive (FEM) problem
• Component supervised network (CSN)
• Dictionary-based implicit-component generator (DICG)