Large Margin Mechanism and Pseudo Query Set on Cross-Domain Few-Shot Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yeh, Jia-Fong, Lee, Hsin-Ying, Tsai, Bing-Chen, Chen, Yi-Rong, Huang, Ping-Chia, Hsu, Winston H.
Format: Preprint
Veröffentlicht: 2020
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917583062564864
author Yeh, Jia-Fong
Lee, Hsin-Ying
Tsai, Bing-Chen
Chen, Yi-Rong
Huang, Ping-Chia
Hsu, Winston H.
author_facet Yeh, Jia-Fong
Lee, Hsin-Ying
Tsai, Bing-Chen
Chen, Yi-Rong
Huang, Ping-Chia
Hsu, Winston H.
contents In recent years, few-shot learning problems have received a lot of attention. While methods in most previous works were trained and tested on datasets in one single domain, cross-domain few-shot learning is a brand-new branch of few-shot learning problems, where models handle datasets in different domains between training and testing phases. In this paper, to solve the problem that the model is pre-trained (meta-trained) on a single dataset while fine-tuned on datasets in four different domains, including common objects, satellite images, and medical images, we propose a novel large margin fine-tuning method (LMM-PQS), which generates pseudo query images from support images and fine-tunes the feature extraction modules with a large margin mechanism inspired by methods in face recognition. According to the experiment results, LMM-PQS surpasses the baseline models by a significant margin and demonstrates that our approach is robust and can easily adapt pre-trained models to new domains with few data.
format Preprint
id arxiv_https___arxiv_org_abs_2005_09218
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Large Margin Mechanism and Pseudo Query Set on Cross-Domain Few-Shot Learning
Yeh, Jia-Fong
Lee, Hsin-Ying
Tsai, Bing-Chen
Chen, Yi-Rong
Huang, Ping-Chia
Hsu, Winston H.
Machine Learning
In recent years, few-shot learning problems have received a lot of attention. While methods in most previous works were trained and tested on datasets in one single domain, cross-domain few-shot learning is a brand-new branch of few-shot learning problems, where models handle datasets in different domains between training and testing phases. In this paper, to solve the problem that the model is pre-trained (meta-trained) on a single dataset while fine-tuned on datasets in four different domains, including common objects, satellite images, and medical images, we propose a novel large margin fine-tuning method (LMM-PQS), which generates pseudo query images from support images and fine-tunes the feature extraction modules with a large margin mechanism inspired by methods in face recognition. According to the experiment results, LMM-PQS surpasses the baseline models by a significant margin and demonstrates that our approach is robust and can easily adapt pre-trained models to new domains with few data.
title Large Margin Mechanism and Pseudo Query Set on Cross-Domain Few-Shot Learning
topic Machine Learning
url https://arxiv.org/abs/2005.09218