MMM
YYYY
Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder
利用噪声增强型有监督自动编码器提高跨域Few-Shot学习的泛化能力
騒音増強型を利用して、自動エンコーダを監督し、ドメインを跨ぐFew-Shot学習の一般化能力を向上させる
소음 증강 형 을 이용 하여 자동 인 코딩 기 를 감독 하여 크로스 필드 Few-Shot 학습 의 일반화 능력 을 향상 시킨다
Mejora de la capacidad de generalización del aprendizaje de la tienda de few de dominio cruzado mediante el uso de codificador automático supervisado mejorado por ruido
Amélioration de la capacité de généralisation de l'apprentissage Multi - domaines par l'utilisation d'un encodeur automatique supervisé amélioré par le bruit
Повышение возможностей обобщения в междоменном обучении за несколько шагов с помощью контролируемого автоэнкодера с повышенным шумом
Hanwen Liang ¹, Qiong Zhang 张琼 ², Peng Dai ¹, Juwei Lu ¹
¹ Huawei Noah’s Ark Lab, Canada
加拿大 华为诺亚方舟实验室
² Department of Statistics, University of British Columbia, Vancouver, Canada
arXiv, 11 August 2021
Abstract

State of the art (SOTA) few-shot learning (FSL) methods suffer significant performance drop in the presence of domain differences between source and target datasets. The strong discrimination ability on the source dataset does not necessarily translate to high classification accuracy on the target dataset.

In this work, we address this cross-domain few-shot learning (CDFSL) problem by boosting the generalization capability of the model. Specifically, we teach the model to capture broader variations of the feature distributions with a novel noise-enhanced supervised autoencoder (NSAE).

NSAE trains the model by jointly reconstructing inputs and predicting the labels of inputs as well as their reconstructed pairs. Theoretical analysis based on intra-class correlation (ICC) shows that the feature embeddings learned from NSAE have stronger discrimination and generalization abilities in the target domain. We also take advantage of NSAE structure and propose a two-step fine-tuning procedure that achieves better adaption and improves classification performance in the target domain.

Extensive experiments and ablation studies are conducted to demonstrate the effectiveness of the proposed method. Experimental results show that our proposed method consistently outperforms SOTA methods under various conditions.
arXiv_1
arXiv_2
arXiv_3
arXiv_4
Reviews and Discussions
https://www.hotpaper.io/index.html
Parametric study on the flutter sensitivity of a wide-chord hollow fan blade
Influence of aspect ratio and arrangement direction on the shear behavior of ellipsoids
Development of a double-layer shaking table for large-displacement high-frequency excitation
Effect of SiC Particle Size on Properties of SiC Porous Ceramics
Physical Layer Authentication in UAV-enabled Relay Networks Based on Manifold Learning
Risk assessment of fault water inrush during deep mining
Simvastatin Improves Outcomes of Endotoxin-induced Coagulopathy by Regulating Intestinal Microenvironment
Sound Insulation Performance of Pyramidal Truss Core Cylindrical Sandwich Structure
Coupling analysis of passenger and train flows for a large-scale urban rail transit system
Effects of minor B additions on tensile strength, fracture toughness and oxidation resistance of Nb–Si based alloys
Essential role of MALAT1 in reducing traumatic brain injury
Seasonal Cumulative Effect of Ural Blocking Episodes on the Frequent Cold events in China during the Early Winter of 2020/21



Previous Article                                Next Article
About
|
Contact
|
Copyright © Hot Paper