# Uncertainty-Aware Few-Shot Image Classification

arXiv: https://arxiv.org/abs/2010.04525 · HTML: https://mlsanity.com/paper/2010.04525/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion](https://mlsanity.com/paper/2304.08183/) (2023)
- [MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learning](https://mlsanity.com/paper/2103.14341/) (2021)
- [Revisiting Local Descriptor for Improved Few-Shot Classification](https://mlsanity.com/paper/2103.16009/) (2021)
- [Towards Few-shot Inductive Link Prediction on Knowledge Graphs: A Relational Anonymous Walk-guided Neural Process Approach](https://mlsanity.com/paper/2307.01204/) (2023)
- [Uncertainty-based Network for Few-shot Image Classification](https://mlsanity.com/paper/2205.08157/) (2022)
- [Graph Mining under Data scarcity](https://mlsanity.com/paper/2406.04825/) (2024)
- [Predictive uncertainty estimation in deep learning for lung carcinoma classification in digital pathology under real dataset shifts](https://mlsanity.com/paper/2408.08432/) (2024)
- [Not All Instances Contribute Equally: Instance-adaptive Class Representation Learning for Few-Shot Visual Recognition](https://mlsanity.com/paper/2209.03034/) (2022)
- [Uncertainty Quantification using Generative Approach](https://mlsanity.com/paper/2310.09338/) (2023)

## Abstract (arXiv)

Few-shot image classification learns to recognize new categories from limited labelled data. Metric learning based approaches have been widely investigated, where a query sample is classified by finding the nearest prototype from the support set based on their feature similarities. A neural network has different uncertainties on its calculated similarities of different pairs. Understanding and modeling the uncertainty on the similarity could promote the exploitation of limited samples in few-shot optimization. In this work, we propose Uncertainty-Aware Few-Shot framework for image classification by modeling uncertainty of the similarities of query-support pairs and performing uncertainty-aware optimization. Particularly, we exploit such uncertainty by converting observed similarities to probabilistic representations and incorporate them to the loss for more effective optimization. In order to jointly consider the similarities between a query and the prototypes in a support set, a graph-based model is utilized to estimate the uncertainty of the pairs. Extensive experiments show our proposed method brings significant improvements on top of a strong baseline and achieves the state-of-the-art performance.