Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation
This work addresses the challenge of few-shot learning for image classification, offering a plug-in method to enhance existing approaches, though it appears incremental as it builds on pretext tasks and hierarchical aggregation.
The paper tackles the problem of improving few-shot image classification by learning additional feature representations from pretext tasks, and presents a hierarchical tree structure-aware method that adaptively selects and aggregates these features to achieve new state-of-the-art performance on four benchmark datasets.
In this paper, we mainly focus on the problem of how to learn additional feature representations for few-shot image classification through pretext tasks (e.g., rotation or color permutation and so on). This additional knowledge generated by pretext tasks can further improve the performance of few-shot learning (FSL) as it differs from human-annotated supervision (i.e., class labels of FSL tasks). To solve this problem, we present a plug-in Hierarchical Tree Structure-aware (HTS) method, which not only learns the relationship of FSL and pretext tasks, but more importantly, can adaptively select and aggregate feature representations generated by pretext tasks to maximize the performance of FSL tasks. A hierarchical tree constructing component and a gated selection aggregating component is introduced to construct the tree structure and find richer transferable knowledge that can rapidly adapt to novel classes with a few labeled images. Extensive experiments show that our HTS can significantly enhance multiple few-shot methods to achieve new state-of-the-art performance on four benchmark datasets. The code is available at: https://github.com/remiMZ/HTS-ECCV22.