Self-Augmentation: Generalizing Deep Networks to Unseen Classes for Few-Shot Learning

04/01/2020
by   Jin-Woo Seo, et al.
0

Few-shot learning aims to classify unseen classes with a few training examples. While recent works have shown that standard mini-batch training with a carefully designed training strategy can improve generalization ability for unseen classes, well-known problems in deep networks such as memorizing training statistics have been less explored for few-shot learning. To tackle this issue, we propose self-augmentation that consolidates regional dropout and self-distillation. Specifically, we exploit a data augmentation technique called regional dropout, in which a patch of an image is substituted into other values. Then, we employ a backbone network that has auxiliary branches with its own classifier to enforce knowledge sharing. Lastly, we present a fine-tuning method to further exploit a few training examples for unseen classes. Experimental results show that the proposed method outperforms the state-of-the-art methods for prevalent few-shot benchmarks and improves the generalization ability.

READ FULL TEXT

page 3

page 5

page 7

page 8

research
09/13/2021

STraTA: Self-Training with Task Augmentation for Better Few-shot Learning

Despite their recent successes in tackling many NLP tasks, large-scale p...
research
05/25/2021

GAN for Vision, KG for Relation: a Two-stage Deep Network for Zero-shot Action Recognition

Zero-shot action recognition can recognize samples of unseen classes tha...
research
04/27/2023

Self-discipline on multiple channels

Self-distillation relies on its own information to improve the generaliz...
research
07/22/2022

Multi-Level Fine-Tuning, Data Augmentation, and Few-Shot Learning for Specialized Cyber Threat Intelligence

Gathering cyber threat intelligence from open sources is becoming increa...
research
04/10/2020

MA 3 : Model Agnostic Adversarial Augmentation for Few Shot learning

Despite the recent developments in vision-related problems using deep ne...
research
04/08/2019

A Closer Look at Few-shot Classification

Few-shot classification aims to learn a classifier to recognize unseen c...
research
09/23/2020

Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning

Deep learning has shown great success in settings with massive amounts o...

Please sign up or login with your details

Forgot password? Click here to reset