Uncertainty-Aware Few-Shot Image Classification

10/09/2020
by   Zhizheng Zhang, et al.
0

Few-shot image classification aims to learn to recognize new categories from limited labelled data. Recently, metric learning based approaches have been widely investigated which classify a query sample by finding the nearest prototype from the support set based on the feature similarities. For few-shot classification, the calculated similarity of a query-support pair depends on both the query and the support. The network has different confidences/uncertainty on the calculated similarities of the different pairs and there are observation noises on the similarity. Understanding and modeling the uncertainty on the similarity could promote better exploitation of the limited samples in optimization. However, this is still underexplored in few-shot learning. In this work, we propose Uncertainty-Aware Few-Shot (UAFS) image classification by modeling uncertainty of the similarities of query-support pairs and performing uncertainty-aware optimization. Particularly, we design a graph-based model to jointly estimate the uncertainty of similarities between a query and the prototypes in the support set. We optimize the network based on the modeled uncertainty by converting the observed similarity to a probabilistic similarity distribution to be robust to observation noises. Extensive experiments show our proposed method brings significant improvements on top of a strong baseline and achieves the state-of-the-art performance.

READ FULL TEXT

page 3

page 7

research
06/13/2021

NDPNet: A novel non-linear data projection network for few-shot fine-grained image classification

Metric-based few-shot fine-grained image classification (FSFGIC) aims to...
research
05/17/2022

Uncertainty-based Network for Few-shot Image Classification

The transductive inference is an effective technique in the few-shot lea...
research
03/21/2021

Hierarchical Representation based Query-Specific Prototypical Network for Few-Shot Image Classification

Few-shot image classification aims at recognizing unseen categories with...
research
04/30/2020

SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentation

Few-shot segmentation (FSS) methods perform image segmentation for a par...
research
09/08/2020

Region Comparison Network for Interpretable Few-shot Image Classification

While deep learning has been successfully applied to many real-world com...
research
11/25/2020

Match Them Up: Visually Explainable Few-shot Image Classification

Few-shot learning (FSL) approaches are usually based on an assumption th...
research
02/09/2022

Improving greedy core-set configurations for active learning with uncertainty-scaled distances

We scale perceived distances of the core-set algorithm by a factor of un...

Please sign up or login with your details

Forgot password? Click here to reset