Task Adaptive Feature Distribution Based Network for Few-shot Fine-grained Target Classification
This work solves the problem of accurate classification in few-shot fine-grained scenarios for computer vision applications, but it appears incremental as it builds on existing metric-based methods.
The paper tackles the problem of few-shot fine-grained classification by proposing TAFD-Net, which addresses issues like task-level special cases and irrelevant sample information, resulting in outperforming recent incremental learning algorithms on three datasets.
Metric-based few-shot fine-grained classification has shown promise due to its simplicity and efficiency. However, existing methods often overlook task-level special cases and struggle with accurate category description and irrelevant sample information. To tackle these, we propose TAFD-Net: a task adaptive feature distribution network. It features a task-adaptive component for embedding to capture task-level nuances, an asymmetric metric for calculating feature distribution similarities between query samples and support categories, and a contrastive measure strategy to boost performance. Extensive experiments have been conducted on three datasets and the experimental results show that our proposed algorithm outperforms recent incremental learning algorithms.