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

arXiv: https://arxiv.org/abs/2410.09797 · HTML: https://mlsanity.com/paper/2410.09797/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 13 Oct 2024.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning](https://mlsanity.com/paper/1903.12290/) (2019)
- [Instance Credibility Inference for Few-Shot Learning](https://mlsanity.com/paper/2003.11853/) (2020)
- [Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition](https://mlsanity.com/paper/1708.02412/) (2017)
- [Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification](https://mlsanity.com/paper/1908.01313/) (2019)
- [BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification](https://mlsanity.com/paper/2011.14311/) (2020)
- [Asymmetric Distribution Measure for Few-shot Learning](https://mlsanity.com/paper/2002.00153/) (2020)
- [TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples](https://mlsanity.com/paper/2005.13820/) (2020)
- [Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning](https://mlsanity.com/paper/1904.03580/) (2019)
- [Hierarchical Representation based Query-Specific Prototypical Network for Few-Shot Image Classification](https://mlsanity.com/paper/2103.11384/) (2021)

## Abstract (arXiv)

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.