Imperial College London
Dr Panagiota (Tania) Stathaki

Dr Panagiota (Tania) Stathaki

Faculty of Engineering, Department of Electrical and Electronic Engineering

Reader in Signal Processing
 
 
 
//

Contact

 

+44 (0)20 7594 6229t.stathaki Website

 
 
//

Assistant

 

Miss Vanessa Rodriguez-Gonzalez +44 (0)20 7594 6267

 
//

Location

 

812Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Lazarou:2022:10.1109/WACV51458.2022.00211,
author = {Lazarou, M and Stathaki, T and Avrithis, Y},
doi = {10.1109/WACV51458.2022.00211},
pages = {2050--2060},
publisher = {IEEE COMPUTER SOC},
title = {Tensor feature hallucination for few-shot learning},
url = {http://dx.doi.org/10.1109/WACV51458.2022.00211},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Few-shot learning addresses the challenge of learning how to address novel tasks 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. The source code can be found at https://github.com/MichalisLazarou/TFH_fewshot.
AU  - Lazarou,M
AU  - Stathaki,T
AU  - Avrithis,Y
DO  - 10.1109/WACV51458.2022.00211
EP  - 2060
PB  - IEEE COMPUTER SOC
PY  - 2022///
SN  - 2472-6737
SP  - 2050
TI  - Tensor feature hallucination for few-shot learning
UR  - http://dx.doi.org/10.1109/WACV51458.2022.00211
UR  - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000800471202012&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://ieeexplore.ieee.org/document/9706713
UR  - http://hdl.handle.net/10044/1/100519
ER  -
Download