Finding Task-Relevant Features for Few-Shot Learning by Category Traversal

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 1 - 10
• Main Authors: Li, Hongyang, Eigen, David, Dodge, Samuel, Zeiler, Matthew, Wang, Xiaogang
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2019
• Subjects: Benchmark testing; Computer vision; Deep Learning; Feature extraction; Few shot learning; Hands; Pattern recognition; Pragmatics; Training
• ISSN: 1063-6919
• DOI: 10.1109/CVPR.2019.00009

Few-shot learning is an important area of research. Conceptually, humans are readily able to understand new concepts given just a few examples, while in more pragmatic terms, limited-example training situations are common practice. Recent effective approaches to few-shot learning employ a metric-learning framework to learn a feature similarity comparison between a query (test) example, and the few support (training) examples. However, these approaches treat each support class independently from one another, never looking at the entire task as a whole. Because of this, they are constrained to use a single set of features for all possible test-time tasks, which hinders the ability to distinguish the most relevant dimensions for the task at hand. In this work, we introduce a Category Traversal Module that can be inserted as a plug-and-play module into most metric-learning based few-shot learners. This component traverses across the entire support set at once, identifying task-relevant features based on both intra-class commonality and inter-class uniqueness in the feature space. Incorporating our module improves performance considerably (5%-10% relative) over baseline systems on both miniImageNet and tieredImageNet benchmarks, with overall performance competitive with the most recent state-of-the-art systems.