MDFM: Multi-Decision Fusing Model for Few-Shot Learning

12/01/2021
by   Shuai Shao, et al.
4

In recent years, researchers pay growing attention to the few-shot learning (FSL) task to address the data-scarce problem. A standard FSL framework is composed of two components: i) Pre-train. Employ the base data to generate a CNN-based feature extraction model (FEM). ii) Meta-test. Apply the trained FEM to the novel data (category is different from base data) to acquire the feature embeddings and recognize them. Although researchers have made remarkable breakthroughs in FSL, there still exists a fundamental problem. Since the trained FEM with base data usually cannot adapt to the novel class flawlessly, the novel data's feature may lead to the distribution shift problem. To address this challenge, we hypothesize that even if most of the decisions based on different FEMs are viewed as weak decisions, which are not available for all classes, they still perform decently in some specific categories. Inspired by this assumption, we propose a novel method Multi-Decision Fusing Model (MDFM), which comprehensively considers the decisions based on multiple FEMs to enhance the efficacy and robustness of the model. MDFM is a simple, flexible, non-parametric method that can directly apply to the existing FEMs. Besides, we extend the proposed MDFM to two FSL settings (i.e., supervised and semi-supervised settings). We evaluate the proposed method on five benchmark datasets and achieve significant improvements of 3.4 state-of-the-arts.

READ FULL TEXT

page 1

page 8

page 9

research
09/16/2021

MHFC: Multi-Head Feature Collaboration for Few-Shot Learning

Few-shot learning (FSL) aims to address the data-scarce problem. A stand...
research
03/15/2022

CSN: Component-Supervised Network for Few-Shot Classification

The few-shot classification (FSC) task has been a hot research topic in ...
research
12/29/2019

FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers

One of the most significant challenges facing a few-shot learning task i...
research
03/14/2020

TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification

The field of Few-Shot Learning (FSL), or learning from very few (typical...
research
09/07/2021

CIM: Class-Irrelevant Mapping for Few-Shot Classification

Few-shot classification (FSC) is one of the most concerned hot issues in...
research
04/15/2023

Instance-level Few-shot Learning with Class Hierarchy Mining

Few-shot learning is proposed to tackle the problem of scarce training d...

Please sign up or login with your details

Forgot password? Click here to reset