Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
This work improves few-shot learning for scenarios with limited training data, such as in computer vision, by enhancing feature relevance, though it is incremental as it builds on existing metric-learning frameworks.
The paper tackles the problem of few-shot learning by addressing the limitation of existing metric-learning approaches that treat support classes independently, proposing a Category Traversal Module to identify task-relevant features based on intra-class commonality and inter-class uniqueness, resulting in a 5%-10% relative performance improvement over baselines on mini-ImageNet and tieredImageNet benchmarks.
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 in 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 mini-ImageNet and tieredImageNet benchmarks, with overall performance competitive with recent state-of-the-art systems.