Tensor feature hallucination for few-shot learning

06/09/2021
by   Michalis Lazarou, et al.
0

Few-shot classification addresses the challenge of classifying examples given not just limited supervision but limited data as well. An attractive solution is synthetic data generation. However, most such methods are overly sophisticated, focusing on high-quality, realistic data in the input space. It is unclear whether adapting them to the few-shot regime and using them for the downstream task of classification is the right approach. Previous works on synthetic data generation for few-shot classification focus on exploiting complex models, e.g. a Wasserstein GAN with multiple regularizers or a network that transfers latent diversities from known to novel classes. We follow a different approach and investigate how a simple and straightforward synthetic data generation method can be used effectively. We make two contributions, namely we show that: (1) using a simple loss function is more than enough for training a feature generator in the few-shot setting; and (2) learning to generate tensor features instead of vector features is superior. Extensive experiments on miniImagenet, CUB and CIFAR-FS datasets show that our method sets a new state of the art, outperforming more sophisticated few-shot data augmentation methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/19/2021

Few-shot learning via tensor hallucination

Few-shot classification addresses the challenge of classifying examples ...
research
12/31/2019

Diversity Transfer Network for Few-Shot Learning

Few-shot learning is a challenging task that aims at training a classifi...
research
08/29/2023

Few-Shot Object Detection via Synthetic Features with Optimal Transport

Few-shot object detection aims to simultaneously localize and classify t...
research
10/27/2018

Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks

Deep neural networks suffer from over-fitting and catastrophic forgettin...
research
04/26/2023

Is a prompt and a few samples all you need? Using GPT-4 for data augmentation in low-resource classification tasks

Obtaining and annotating data can be expensive and time-consuming, espec...
research
06/21/2022

KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Few-Shot NLP

This paper focuses on text data augmentation for few-shot NLP tasks. The...
research
08/19/2019

A Kings Ransom for Encryption: Ransomware Classification using Augmented One-Shot Learning and Bayesian Approximation

Newly emerging variants of ransomware pose an ever-growing threat to com...

Please sign up or login with your details

Forgot password? Click here to reset