Enhancing Prototypical Few-Shot Learning by Leveraging the Local-Level Strategy

11/08/2021
by   Junying Huang, et al.
0

Aiming at recognizing the samples from novel categories with few reference samples, few-shot learning (FSL) is a challenging problem. We found that the existing works often build their few-shot model based on the image-level feature by mixing all local-level features, which leads to the discriminative location bias and information loss in local details. To tackle the problem, this paper returns the perspective to the local-level feature and proposes a series of local-level strategies. Specifically, we present (a) a local-agnostic training strategy to avoid the discriminative location bias between the base and novel categories, (b) a novel local-level similarity measure to capture the accurate comparison between local-level features, and (c) a local-level knowledge transfer that can synthesize different knowledge transfers from the base category according to different location features. Extensive experiments justify that our proposed local-level strategies can significantly boost the performance and achieve 2.8 different benchmark datasets, which also achieves state-of-the-art accuracy.

READ FULL TEXT
research
02/29/2020

Learning to Compare Relation: Semantic Alignment for Few-Shot Learning

Few-shot learning is a fundamental and challenging problem since it requ...
research
08/18/2020

Dataset Bias in Few-shot Image Recognition

The goal of few-shot image recognition (FSIR) is to identify novel categ...
research
08/07/2020

Revisiting Mid-Level Patterns for Distant-Domain Few-Shot Recognition

Cross-domain few-shot learning (FSL) is proposed recently to transfer kn...
research
03/03/2021

Touchless Palmprint Recognition based on 3D Gabor Template and Block Feature Refinement

With the growing demand for hand hygiene and convenience of use, palmpri...
research
05/09/2018

Creative Invention Benchmark

In this paper we present the Creative Invention Benchmark (CrIB), a 2000...
research
06/06/2020

Leveraging the Feature Distribution in Transfer-based Few-Shot Learning

Few-shot classification is a challenging problem due to the uncertainty ...
research
11/21/2019

Knowledge Graph Transfer Network for Few-Shot Recognition

Few-shot learning aims to learn novel categories from very few samples g...

Please sign up or login with your details

Forgot password? Click here to reset