Diversity Transfer Network for Few-Shot Learning

12/31/2019
by   Mengting Chen, et al.
12

Few-shot learning is a challenging task that aims at training a classifier for unseen classes with only a few training examples. The main difficulty of few-shot learning lies in the lack of intra-class diversity within insufficient training samples. To alleviate this problem, we propose a novel generative framework, Diversity Transfer Network (DTN), that learns to transfer latent diversities from known categories and composite them with support features to generate diverse samples for novel categories in feature space. The learning problem of the sample generation (i.e., diversity transfer) is solved via minimizing an effective meta-classification loss in a single-stage network, instead of the generative loss in previous works. Besides, an organized auxiliary task co-training over known categories is proposed to stabilize the meta-training process of DTN. We perform extensive experiments and ablation studies on three datasets, i.e., miniImageNet, CIFAR100 and CUB. The results show that DTN, with single-stage training and faster convergence speed, obtains the state-of-the-art results among the feature generation based few-shot learning methods. Code and supplementary material are available at: https://github.com/Yuxin-CV/DTN

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/22/2020

Few-Shot Learning with Intra-Class Knowledge Transfer

We consider the few-shot classification task with an unbalanced dataset,...
research
10/30/2022

Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid

Few-shot learning (FSL) targets at generalization of vision models towar...
research
01/09/2022

Semantics-driven Attentive Few-shot Learning over Clean and Noisy Samples

Over the last couple of years few-shot learning (FSL) has attracted grea...
research
11/29/2022

Disentangled Generation with Information Bottleneck for Few-Shot Learning

Few-shot learning (FSL), which aims to classify unseen classes with few ...
research
07/12/2023

Rethinking Mitosis Detection: Towards Diverse Data and Feature Representation

Mitosis detection is one of the fundamental tasks in computational patho...
research
06/29/2020

Improving Few-Shot Learning using Composite Rotation based Auxiliary Task

In this paper, we propose an approach to improve few-shot classification...
research
06/09/2021

Tensor feature hallucination for few-shot learning

Few-shot classification addresses the challenge of classifying examples ...

Please sign up or login with your details

Forgot password? Click here to reset