Self-Supervised Animation Synthesis Through Adversarial Training
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Access"
DOI: 10.1109/access.2020.3008523
Abstract: In this paper, we propose a novel deep generative model for image animation synthesis. Based on self-supervised learning and adversarial training, the model can find labeling rules and mark them without origin sample labels. In… read more here.
Keywords: self supervised; adversarial training; animation synthesis; animation ... See more keywords
Learning Consistency From High-Confidence Pseudo-Labels for Weakly Supervised Object Localization
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Access"
DOI: 10.1109/access.2023.3246259
Abstract: Weakly supervised object localization (WSOL) tasks aim to classify and locate a single object under the supervision of only image-level labels. Pseudo-supervised learning methods have been shown to be effective for WSOL. These methods divide… read more here.
Keywords: localization; confidence pseudo; pseudo labels; pseudo ... See more keywords
Semisupervised Deep Convolutional Neural Networks Using Pseudo Labels for PolSAR Image Classification
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Geoscience and Remote Sensing Letters"
DOI: 10.1109/lgrs.2020.3036387
Abstract: Deep-learning-based methods have obtained satisfying results in polarimetric synthetic aperture radar (PolSAR) image classification. However, these methods require large numbers of labeled samples, which are usually time-consuming and high-priced for PolSAR images. To address this… read more here.
Keywords: pseudo labels; labeled samples; classification; polsar image ... See more keywords
Semi-Supervised Text Detection With Accurate Pseudo-Labels
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Signal Processing Letters"
DOI: 10.1109/lsp.2022.3175667
Abstract: Recent scene text detection methods have made great progress. However, existing methods rely heavily on extensive labeled data, which is very time-consuming and expensive. In this letter, we propose a novel semi-supervised text detection method… read more here.
Keywords: accurate pseudo; semi supervised; pseudo labels; pseudo ... See more keywords
Weakly Supervised Region of Interest Extraction Based on Uncertainty-Aware Self-Refinement Learning for Remote Sensing Images
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Geoscience and Remote Sensing"
DOI: 10.1109/tgrs.2022.3199028
Abstract: Region of interest (ROI) extraction plays a significant role in the field of remote sensing image (RSI) processing. Recently, weakly supervised ROI extraction methods have attracted considerable attention due to low labeling cost. Most of… read more here.
Keywords: remote sensing; weakly supervised; uncertainty aware; extraction ... See more keywords
Unsupervised Deep Hashing With Pseudo Labels for Scalable Image Retrieval
Sign Up to like & getrecommendations! Published in 2018 at "IEEE Transactions on Image Processing"
DOI: 10.1109/tip.2017.2781422
Abstract: In order to achieve efficient similarity searching, hash functions are designed to encode images into low-dimensional binary codes with the constraint that similar features will have a short distance in the projected Hamming space. Recently,… read more here.
Keywords: pseudo labels; pseudo; image; deep hashing ... See more keywords
Meta-Reweighted Regularization for Unsupervised Domain Adaptation
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Knowledge and Data Engineering"
DOI: 10.1109/tkde.2021.3114536
Abstract: Unsupervised domain adaptation (UDA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy, and the adversarial learning based paradigm has achieved remarkable success. On top… read more here.
Keywords: domain adaptation; pseudo labels; unsupervised domain; domain ... See more keywords
Segmentation of HE-stained meningioma pathological images based on pseudo-labels
Sign Up to like & getrecommendations! Published in 2022 at "PLoS ONE"
DOI: 10.1371/journal.pone.0263006
Abstract: Biomedical research is inseparable from the analysis of various histopathological images, and hematoxylin-eosin (HE)-stained images are one of the most basic and widely used types. However, at present, machine learning based approaches of the analysis… read more here.
Keywords: based pseudo; segmentation stained; pseudo labels; machine learning ... See more keywords
PLDH: Pseudo-Labels Based Deep Hashing
Sign Up to like & getrecommendations! Published in 2023 at "Mathematics"
DOI: 10.3390/math11092175
Abstract: Deep hashing has received a great deal of attraction in large-scale data analysis, due to its high efficiency and effectiveness. The performance of deep hashing models heavily relies on label information, which is very expensive… read more here.
Keywords: labels based; pseudo labels; deep hashing; based deep ... See more keywords
SNPD: Semi-Supervised Neural Process Dehazing Network with Asymmetry Pseudo Labels
Sign Up to like & getrecommendations! Published in 2022 at "Symmetry"
DOI: 10.3390/sym14040806
Abstract: Haze can cause a significant reduction in the contrast and brightness of images. CNN-based methods have achieved benign performance on synthetic data. However, they show weak generalization performance on real data because they are only… read more here.
Keywords: network; neural process; semi supervised; pseudo labels ... See more keywords