• Home
  • Search
  • Unsupervised Embedding Learning by Noisy Similarity Label Optimization
  • Cite Icon1
  • https://doi.org/10.1109/vcip49819.2020.9301761Copy DOI Icon

Unsupervised Embedding Learning by Noisy Similarity Label Optimization

  • Dec 1, 2020
  • Koki Tsubota +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

We propose a similarity label optimization framework for unsupervised embedding learning. Existing works use similarity labels obtained from instance labels, which are image identifiers, for unsupervised embedding learning assuming that images of different instance labels have different semantic classes. However, because of the significant semantic gap between classes and instances, instance labels are not enough for learning embeddings. To alleviate this problem, we consider the similarity labels as noisy labels and optimize similarity labels and neural network parameters in an alternating fashion. Experimental results demonstrate that the proposed method outperforms a baseline method by 1.2% in terms of accuracy on the CIFAR-10 dataset and in 1.3% in terms of recall at k (k = 1) on the Stanford Online Product dataset.

Similar Papers
  • Research Article
  • Citations12

Usr-mtl: an unsupervised sentence representation learning framework with multi-task learning

  • Nov 14, 2020
  • Applied Intelligence
  • Wenshen Xu +2
  • Conference Article
  • Citations6

Unsupervised Ensemble Learning with Noisy Label Correction

  • Jul 11, 2021
  • Xupeng Zou +3
  • PDF
  • Research Article
  • Citations77

ResNet Autoencoders for Unsupervised Feature Learning From High-Dimensional Data: Deep Models Resistant to Performance Degradation

  • Jan 01, 2021
  • IEEE Access
  • Chathurika S Wickramasinghe +2
  • Research Article
  • Citations81

Consensus unsupervised feature ranking from multiple views

  • Dec 08, 2007
  • Pattern Recognition Letters
  • Yi Hong +3
  • Research Article

Unsupervised Feature Selection-Driven Active Learning for Semi-Supervised Automatic ECG Analysis.

  • Jan 01, 2025
  • IEEE journal of biomedical and health informatics
  • Xiao Li +8
  • Book Chapter
  • Citations6

Unsupervised Selective Transfer Learning for Object Recognition

  • Jan 01, 2011
  • Wei-Shi Zheng +2
  • Book Chapter
  • Citations8

Multi-view Brain HyperConnectome AutoEncoder for Brain State Classification

  • Jan 01, 2020
  • Alin Banka +2
  • Conference Article
  • Citations1

SoundRate: Distributed Acoustic Sensing for Autonomous Flow Allocation via Unsupervised Learning

  • Nov 03, 2025
  • P Moradi +2
  • Conference Article
  • Citations62

RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes

  • Jun 01, 2022
  • Tak-Wai Hui
  • Research Article
  • Citations10

Bag of shape descriptor using unsupervised deep learning for non-rigid shape recognition

  • Apr 20, 2021
  • Signal Processing: Image Communication
  • Linjie Yang +3
  • Conference Article
  • Citations1

Contextual Image Parsing via Panoptic Segment Sorting

  • Oct 20, 2021
  • Jyh-Jing Hwang +2
  • Research Article
  • Citations6

Deep Variation Prior: Joint Image Denoising and Noise Variance Estimation without Clean Data.

  • Jan 01, 2024
  • IEEE Transactions on Image Processing
  • Rihuan Ke
  • Research Article
  • Citations16

Graph prototypical contrastive learning

  • Sep 11, 2022
  • Information Sciences
  • Meixin Peng +2
  • Conference Article
  • Citations2

Self Error Detection and Correction for Noisy Labels Based on Error Correcting Output Code in Convolutional Neural Networks

  • Jan 01, 2019
  • Yang Jiao +2
  • Research Article

Deep Learning from Noisy Labels with Some Adjustments of a Recent Method

  • Jan 01, 2023
  • Infocommunications journal
  • István Fazekas +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.