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

05/19/2020
by   Jia-Fong Yeh, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/16/2019

A New Benchmark for Evaluation of Cross-Domain Few-Shot Learning

Recent progress on few-shot learning has largely re-lied on annotated da...
research
09/28/2020

Interventional Few-Shot Learning

We uncover an ever-overlooked deficiency in the prevailing Few-Shot Lear...
research
09/16/2021

MHFC: Multi-Head Feature Collaboration for Few-Shot Learning

Few-shot learning (FSL) aims to address the data-scarce problem. A stand...
research
12/03/2020

SB-MTL: Score-based Meta Transfer-Learning for Cross-Domain Few-Shot Learning

While many deep learning methods have seen significant success in tackli...
research
05/25/2021

Matching Targets Across Domains with RADON, the Re-Identification Across Domain Network

We present a novel convolutional neural network that learns to match ima...
research
07/06/2021

Generalizing Nucleus Recognition Model in Multi-source Images via Pruning

Ki67 is a significant biomarker in the diagnosis and prognosis of cancer...
research
11/27/2022

Cross-domain Few-shot Segmentation with Transductive Fine-tuning

Few-shot segmentation (FSS) expects models trained on base classes to wo...

Please sign up or login with your details

Forgot password? Click here to reset