Task Adaptive Feature Distribution Based Network for Few-shot Fine-grained Target Classification

TL;DR

TAFD-Net is a novel network for few-shot fine-grained classification that adaptively captures task-specific nuances and improves similarity measurement, leading to superior performance over recent methods.

Contribution

It introduces a task-adaptive embedding, an asymmetric metric, and a contrastive measure strategy to enhance few-shot fine-grained classification.

Findings

Outperforms recent incremental learning algorithms on three datasets.

Effectively captures task-level nuances and irrelevant sample information.

Improves accuracy in few-shot fine-grained classification tasks.

Abstract

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.