• Home
  • Search
  • Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder
  • Open Access IconOpen Access
  • Cite Icon77
  • https://doi.org/10.1109/iccv48922.2021.00929Copy DOI Icon

Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder

  • Oct 1, 2021
  • Hanwen Liang +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
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.

Similar Papers
  • Conference Article
  • Citations3

SLA+: Narrowing the Difference between Data Sets in Heterogenous Cross-Project Defection Prediction

  • Jul 01, 2020
  • Jie Wu +3
  • Conference Article
  • Citations3

A novel H and E color augmentation for domain invariance classification of unannotated histopathology prostate cancer images

  • Apr 07, 2023
  • Roozbeh Bazargani +7
  • Research Article
  • Citations1

IT-RUDA: Information Theory Assisted Robust Unsupervised Domain Adaptation

  • Apr 28, 2025
  • ACM Transactions on Intelligent Systems and Technology
  • Shima Rashidi +9
  • Research Article
  • Citations20

A Transfer Reinforcement Learning Framework for Smart Home Energy Management Systems

  • Feb 15, 2023
  • IEEE Sensors Journal
  • Murad Khan +4
  • PDF
  • Research Article
  • Citations8

Multiple-level biomedical event trigger recognition with transfer learning

  • Sep 06, 2019
  • BMC Bioinformatics
  • Yifei Chen
  • Research Article

Transferability of radiomics models between deep learning and conventional CT reconstruction algorithms: A task-based assessment for stratifying acute pancreatitis severity.

  • Mar 25, 2026
  • Journal of applied clinical medical physics
  • Xiaobao Hu +6
  • Conference Article
  • Citations61

Ranking Distance Calibration for Cross-Domain Few-Shot Learning

  • Jun 01, 2022
  • Pan Li +3
  • Research Article
  • Citations1

Adaptive Transfer Learning for Time-to-Event Modeling with Applications in Disease Risk Assessment.

  • May 12, 2025
  • medRxiv : the preprint server for health sciences
  • Yuying Lu +2
  • Research Article
  • Citations1

Adaptive transfer learning for time-to-event modeling with applications in disease risk assessment.

  • Jan 20, 2026
  • Biostatistics (Oxford, England)
  • Yuying Lu +2
  • Research Article
  • Citations29

Generalized Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data.

  • Jan 01, 2022
  • IEEE Transactions on Image Processing
  • Yuqian Fu +3
  • Research Article
  • Citations18

A Data Transfer and Relevant Metrics Matching Based Approach for Heterogeneous Defect Prediction

  • Mar 01, 2023
  • IEEE Transactions on Software Engineering
  • Pravas Ranjan Bal +1
  • Research Article
  • Citations26

A topic sentence-based instance transfer method for imbalanced sentiment classification of Chinese product reviews

  • Oct 30, 2015
  • Electronic Commerce Research and Applications
  • Feng Tian +6
  • Research Article
  • Citations28

Multi-branch feature transformation cross-domain few-shot learning for hyperspectral image classification

  • Nov 20, 2024
  • Pattern Recognition
  • Meilin Shi +1
  • Research Article
  • Citations2

ScMUSCL: multi-source transfer learning for clustering scRNA-seq data.

  • Mar 27, 2025
  • Bioinformatics (Oxford, England)
  • Arash Khoeini +4
  • Research Article
  • Citations1

Using Incremental Learning With Rehearsal to Enhance Global Collapse Prediction Machine Learning Models Across Diverse Steel Building Datasets

  • Dec 02, 2025
  • The Structural Design of Tall and Special Buildings
  • Prakash Gaire +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.