Few-shot learning with improved local representations via bias rectify module

11/01/2021
by   Chao Dong, et al.
0

Recent approaches based on metric learning have achieved great progress in few-shot learning. However, most of them are limited to image-level representation manners, which fail to properly deal with the intra-class variations and spatial knowledge and thus produce undesirable performance. In this paper we propose a Deep Bias Rectify Network (DBRN) to fully exploit the spatial information that exists in the structure of the feature representations. We first employ a bias rectify module to alleviate the adverse impact caused by the intra-class variations. bias rectify module is able to focus on the features that are more discriminative for classification by given different weights. To make full use of the training data, we design a prototype augment mechanism that can make the prototypes generated from the support set to be more representative. To validate the effectiveness of our method, we conducted extensive experiments on various popular few-shot classification benchmarks and our methods can outperform state-of-the-art methods.

READ FULL TEXT

page 2

page 3

research
11/25/2019

Prototype Rectification for Few-Shot Learning

Few-shot learning is a challenging problem that requires a model to reco...
research
06/15/2020

LFD-ProtoNet: Prototypical Network Based on Local Fisher Discriminant Analysis for Few-shot Learning

The prototypical network (ProtoNet) is a few-shot learning framework tha...
research
03/15/2020

DeepEMD: Few-Shot Image Classification with Differentiable Earth Mover's Distance and Structured Classifiers

In this paper, we address the few-shot classification task from a new pe...
research
05/27/2019

Finding Task-Relevant Features for Few-Shot Learning by Category Traversal

Few-shot learning is an important area of research. Conceptually, humans...
research
09/27/2021

Sparse Spatial Transformers for Few-Shot Learning

Learning from limited data is a challenging task since the scarcity of d...
research
06/16/2021

ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning

Recently, the transductive graph-based methods have achieved great succe...
research
11/22/2021

ShufaNet: Classification method for calligraphers who have reached the professional level

The authenticity of calligraphy is significant but difficult task in the...

Please sign up or login with your details

Forgot password? Click here to reset