A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Reconstruction Regularized Deep Metric Learning for Multi-label Image Classification
[article]
2020
arXiv
pre-print
In this paper, we present a novel deep metric learning method to tackle the multi-label image classification problem. ...
Moreover, a reconstruction module for recovering correct labels is incorporated into the whole framework as a regularization term, such that the label embedding space is more representative. ...
Deep learning for multi-label image classification: Recently, deep learning has been gradually applied to multi-label image classification. ...
arXiv:2007.13547v1
fatcat:6slei7dv25ej5hcs5vqsztc7uq
Representation Learning with Dual Autoencoder for Multi-label Classification
2021
IEEE Access
[16] combined recurrent neural networks (RNNs) with deep convolutional neural networks (CNNs) for multi-label image classification, and a joint image-label embedding is learned to model the label co-occurrence ...
multi-label image recognition. ...
His research interests include pattern recognition, machine learning, multimedia search, and information fusion. ...
doi:10.1109/access.2021.3096194
fatcat:tukpui6eczdjnixhs2lbokmfum
A Tetrahedron-Based Heat Flux Signature for Cortical Thickness Morphometry Analysis
[chapter]
2018
Lecture Notes in Computer Science
PET Reconstruction 520 Joint Prediction and Classification of Brain Image Evolution Trajectories from Baseline Brain Image with Application to Early Dementia 528 IMAGE SEGMENTATION AND CLASSIFICATION ...
Data With Autoencoder Based Regularization 656 Multi-Label Transduction for Identifying Disease Comorbidity Patterns 659 Training Multi-organ Segmentation Networks with Sample Selection by Relaxed Upper ...
doi:10.1007/978-3-030-00931-1_48
pmid:30338317
pmcid:PMC6191198
fatcat:dqhvpm5xzrdqhglrfftig3qejq
Supervised COSMOS Autoencoder: Learning Beyond the Euclidean Loss!
[article]
2018
arXiv
pre-print
Autoencoders are unsupervised deep learning models used for learning representations. ...
While this can be useful for applications related to unsupervised reconstruction, it may not be optimal for classification. ...
This implies that for an input image (a), a Euclidean distance based autoencoder (that is used for classification) may prefer having (b) or (c) at the reconstruction layer, i.e. images
Encoding Layers ...
arXiv:1810.06221v1
fatcat:f2gcbwmdpfdsrki3zlopmkvjdq
Table of contents
2020
IEEE Transactions on Neural Networks and Learning Systems
Reconstruction Regularized Deep Metric Learning for Multi-Label Image Classification .................................. ................................................................................ ...
Zheng 2294 RoSeq: Robust Sequence Labeling ......................... J. T. Zhou, H. Zhang, D. Jin, X. Peng, Y. Xiao, and Z. Cao 2304 Does Tail Label Help for Large-Scale Multi-Label Learning? ...
doi:10.1109/tnnls.2020.3003486
fatcat:6kngm3u5xbfr3g5hskhzc6s2ny
Anomaly Detection in Retinal Images using Multi-Scale Deep Feature Sparse Coding
[article]
2022
arXiv
pre-print
These CNN models frequently rely on vast amounts of labeled data for training, difficult to obtain, especially for rare diseases. ...
We have introduced an unsupervised approach for detecting anomalies in retinal images to overcome this issue. ...
Multi-Scale Deep Feature Sparse Coding (MDFSC) for anomaly detection to adopt a different type of datasets, We extended Multi-Scale Deep Feature Sparse Coding (MDFSC) from sparse coding for various types ...
arXiv:2201.11506v1
fatcat:mzoezgkxjrae7f6pltgxiuhnom
ReConTab: Regularized Contrastive Representation Learning for Tabular Data
[article]
2023
arXiv
pre-print
In response to this challenge, we introduce ReConTab, a deep automatic representation learning framework with regularized contrastive learning. ...
Specifically, regularization techniques are applied for raw feature selection. Meanwhile, ReConTab leverages contrastive learning to distill the most pertinent information for downstream tasks. ...
However, for the two multi-class datasets, VO and MN, we utilize accuracy on the test set as the metric for comparing performance. ...
arXiv:2310.18541v2
fatcat:wizcmzko3namxjfjthparl44bq
Domain Adaptation for Visual Applications: A Comprehensive Survey
[article]
2017
arXiv
pre-print
Fourth, we overview the methods that go beyond image categorization, such as object detection or image segmentation, video analyses or learning visual attributes. ...
Third, we discuss the effect of the success of deep convolutional architectures which led to new type of domain adaptation methods that integrate the adaptation within the deep architecture. ...
[4] explores various metric learning approaches to align deep features extracted from RGB and NIR face images. ...
arXiv:1702.05374v2
fatcat:5va4oz4evjfhxgxddflpbb6pxi
Deep Co-Attention Network for Multi-View Subspace Learning
[article]
2021
arXiv
pre-print
To address these issues, in this paper, we propose a deep co-attention network for multi-view subspace learning, which aims to extract both the common information and the complementary information in an ...
In particular, it uses a novel cross reconstruction loss and leverages the label information to guide the construction of the latent representation by incorporating the classifier into our model. ...
canonical correlated auto-encoders for two views; Deep IB [33],
deep information bottleneck for multi-view learning. ...
arXiv:2102.07751v1
fatcat:ufmiwpf7szbpzkrw6go7fv72ru
Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directions
[article]
2023
arXiv
pre-print
Thus, label-efficient deep learning methods are developed to make comprehensive use of the labeled data as well as the abundance of unlabeled and weak-labeled data. ...
Deep learning has seen rapid growth in recent years and achieved state-of-the-art performance in a wide range of applications. ...
Aside from leveraging conventional metrics, utilizing metrics from the deep learning model is another trend. ...
arXiv:2303.12484v4
fatcat:hfuzqtc76vfnzl6iunurrtoq4y
Deep Visual Domain Adaptation: A Survey
[article]
2018
arXiv
pre-print
Deep domain adaption has emerged as a new learning technique to address the lack of massive amounts of labeled data. ...
There have been comprehensive surveys for shallow domain adaption, but few timely reviews the emerging deep learning based methods. ...
The deep reconstruction classification network (DRCN) architecture. ...
arXiv:1802.03601v4
fatcat:d5hwwecipjfjzmh7725lmepzfe
Metric-based Regularization and Temporal Ensemble for Multi-task Learning using Heterogeneous Unsupervised Tasks
[article]
2019
arXiv
pre-print
To overcome this problem, we propose the metric-based regularization term and temporal task ensemble (TTE) for multi-task learning. ...
Experimental results for three target tasks such as classification, object detection and embedding clustering prove that the TTE-based multi-task framework is more effective than the state-of-the-art ( ...
(6) is the KLD between the label image and the reconstructed image for the basic regularization effect. ...
arXiv:1908.11024v1
fatcat:zzxxoec32vefdfxqcjvoudorgu
Training Methods of Multi-label Prediction Classifiers for Hyperspectral Remote Sensing Images
[article]
2023
arXiv
pre-print
Unlike applications that focus on single-label, pixel-level classification methods for hyperspectral remote sensing images, we propose a multi-label, patch-level classification method based on a two-component ...
Yet, deep learning methods known for their representation learning capabilities prove more suitable for handling such complexities. ...
Acknowledgments The research presented in this article is part of the project "Learning-based representations for the automation of hyperspectral microscopic imaging and predictive maintenance" funded ...
arXiv:2301.06874v2
fatcat:wwjlaw6aenbrrdvbrjo2h5keiq
Multi-task Deep Learning Based CT Imaging Analysis For COVID-19: Classification and Segmentation
[article]
2020
medRxiv
pre-print
Our architecture is composed by an encoder and two decoders for reconstruction and segmentation, and a multi-layer perceptron for classification. ...
In this work, we propose a multitask deep learning model to jointly identify COVID-19 patient and segment COVID-19 lesion from chest CT images. ...
In this work, we propose a novel multi-task deep learning model for jointly detecting COVID-19 image and segmenting lesions. ...
doi:10.1101/2020.04.16.20064709
fatcat:bosckhuakrgx7haewgwjxh7rzu
Deep learning for multi-label land cover classification
2015
Image and Signal Processing for Remote Sensing XXI
In this work, we investigate feature learning as a feature extraction process in order to identify the underlying explanatory patterns hidden in low-level satellite data for the purpose of multi-label ...
The results suggest that learning such sparse and abstract representations of the features can aid in both remote sensing and multi-label problems. ...
. • multi-label classification through the learned feature-mapping. ...
doi:10.1117/12.2195082
fatcat:zzmll5mh5bagniowox2kricena
« Previous
Showing results 1 — 15 out of 18,492 results