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
Unimodal probability distributions for deep ordinal classification
[article]
2017
arXiv
pre-print
Preserved Fulltext
Other Versions
Probability distributions produced by the cross-entropy loss for ordinal classification problems can possess undesired properties. ...
We propose a straightforward technique to constrain discrete ordinal probability distributions to be unimodal via the use of the Poisson and binomial probability distributions. ...
arXiv:1705.05278v2 [stat.ML] 22 Jun 2017 Unimodal Probability Distributions for Deep Ordinal Classification
(a) An adult woman
baby
kid
schooler
teen
adult
senior
elder
distribution A
p(y ...
arXiv:1705.05278v2
fatcat:t2ymgim5mzh5zccbezpefiu45m
Deep Ordinal Regression using Optimal Transport Loss and Unimodal Output Probabilities
[article]
2021
arXiv
pre-print
Preserved Fulltext
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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2011.07607v1 fatcat:mgnbjcc735gplegzsumgxqre2u
In this work, we propose a framework for deep ordinal regression, based on unimodal output distribution and optimal transport loss. ...
ordinal regression with unimodal output probabilities, while having guarantee on the output unimodality. ...
Conclusion In this manuscript we presented an approach for deep ordinal regression, inspired by the proportional odds model, utilizing an architectural mechanism for generation of unimodal output probabilities ...
arXiv:2011.07607v2
fatcat:fcjo2chbqbbilluei6tynfq7wu
Quasi-Unimodal Distributions for Ordinal Classification
2022
Mathematics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
For that reason, many losses have been proposed in the literature, which model the output probabilities as following a unimodal distribution. ...
Ordinal classification tasks are present in a large number of different domains. ...
Contributions: For neural networks, a novel non-parametric ordinal loss is presented that induces output probabilities to follow a quasi-unimodal distribution. ...
doi:10.3390/math10060980
fatcat:t7zf3qulz5h35m2rbpz27bs2dm
Ordinal losses for classification of cervical cancer risk
2021
PeerJ Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
A non-parametric ordinal loss for neuronal networks is proposed that promotes the output probabilities to follow a unimodal distribution. ...
Current approaches to ordinal inference for neural networks are found to not sufficiently take advantage of the ordinal problem or to be too uncompromising. ...
It would be preferable for output probabilities to follow a unimodal distribution, as depicted by Fig. 1 . ...
doi:10.7717/peerj-cs.457
pmid:33981833
pmcid:PMC8080423
fatcat:ago3kcbqbng3fny6pjp6eqjq2y
Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Second, the probabilities of neighboring labels should decrease with the increase of distance away from the ground-truth, i.e., the distribution is unimodal. ...
Under the premise of these principles, we propose a novel loss function for fully adaptive label distribution learning, namely unimodal-concentrated loss. ...
Unimodal loss Based on the principles we have summarized previously, it is crucial to output a unimodal distribution for ordinal regression tasks. ...
arXiv:2204.00309v1
fatcat:px6azhv7qbd4fme5eqptoxfi6e
Unimodal regularisation based on beta distribution for deep ordinal regression
2021
Pattern Recognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Currently, the use of deep learning for solving ordinal classification problems, where categories follow a natural order, has not received much attention. ...
This regularisation encourages the distribution of the labels to be a soft unimodal distribution, more appropriate for ordinal problems. ...
ordinal classification problems where the output distribution should be unimodal. ...
doi:10.1016/j.patcog.2021.108310
fatcat:gmblepvzenh3zfil45frtjlk4e
COLD Fusion: Calibrated and Ordinal Latent Distribution Fusion for Uncertainty-Aware Multimodal Emotion Recognition
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In particular, we impose Calibration and Ordinal Ranking constraints on the variance vectors of audiovisual latent distributions. ...
To this end, we propose a novel fusion framework in which we first learn latent distributions over audiovisual temporal context vectors separately, and then constrain the variance vectors of unimodal latent ...
COLD: Calibrated and Ordinal Latent Distributions To effectively learn the unimodal latent distributions for uncertainty-aware fusion, we propose to condition their variance values by applying optimisation ...
arXiv:2206.05833v1
fatcat:7skw5owwpndkdgwrbmlymwwexu
Unimodal-uniform Constrained Wasserstein Training for Medical Diagnosis
[article]
2019
arXiv
pre-print
Preserved Fulltext
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.
Meanwhile, this paper also proposes of constructing the smoothed target labels that model the inlier and outlier noises by using a unimodal-uniform mixture distribution. ...
This labeling system is common for medical disease. Previous methods usually construct a multi-binary-classification task or propose some re-parameter schemes in the output unit. ...
a unimodal-uniform mixture distribution, we also implicitly encourage the probabilities to distribute on the neighbor classes of j * . ...
arXiv:1911.02475v1
fatcat:vsiqaverwrbytb4abgbu4wsgpe
Non-parametric Uni-modality Constraints for Deep Ordinal Classification
[article]
2020
arXiv
pre-print
Preserved Fulltext
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.
Other Versions
(https://github.com/sbelharbi/unimodal-prob-deep-oc-free-distribution) ...
We propose a new constrained-optimization formulation for deep ordinal classification, in which uni-modality of the label distribution is enforced implicitly via a set of inequality constraints over all ...
solution for deep ordinal classification. ...
arXiv:1911.10720v3
fatcat:c2tvsha6vnfxdiiuxxxgbtlkpm
Cumulative link models for deep ordinal classification
[article]
2019
arXiv
pre-print
Preserved Fulltext
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.
Other Versions
This paper proposes a deep convolutional neural network model for ordinal regression by considering a family of probabilistic ordinal link functions in the output layer. ...
The experiments run over two different ordinal classification problems and the statistical tests confirm that these models improve the results of a nominal model and outperform other robust proposals considered ...
Unimodal probability distributions Beckham and Pal [26] proposed a straightforward technique to constrain discrete ordinal probability distributions to be unimodal, via the use of the Poisson and binomial ...
arXiv:1905.13392v2
fatcat:7hkl64srvfggjdujfzc6hw2vdi
Class Distance Weighted Cross-Entropy Loss for Ulcerative Colitis Severity Estimation
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
On the other hand, most studies use categorical cross-entropy loss function to train deep learning models, which is not optimal for the ordinal regression problem. ...
ordinal regression problems. ...
This approach enforces unimodality by punishing inconsistencies in the posterior probability distribution among adjacent labels. ...
arXiv:2202.05167v2
fatcat:t2vaw6u3wndt7avp556rj4s2f4
Multi stain graph fusion for multimodal integration in pathology
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Broadly, this paper demonstrates the value of leveraging diverse pathology images for improved ML-powered histologic assessment. ...
Deep learning methods for WSI analysis Deep learning has achieved unparalleled success in histopathology image analysis and enabled the fast, accurate, and robust classification of complex cell and tissue ...
This combined representation is passed to a feed-forward network that performs the downstream ordinal classification. ...
arXiv:2204.12541v1
fatcat:wkulvrymevgflhhrbyue74cvra
Meta Ordinal Regression Forest for Medical Image Classification with Ordinal Labels
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
To improve model generalization with ordinal information, we propose a novel meta ordinal regression forest (MORF) method for medical image classification with ordinal labels, which learns the ordinal ...
The performance of medical image classification has been enhanced by deep convolutional neural networks (CNNs), which are typically trained with cross-entropy (CE) loss. ...
However, CE loss is inferior for fitting the ordinal distribution of labels. ...
arXiv:2203.07725v1
fatcat:euv64kmbmjbujbkxhlz4lyt6n4
Conservative Wasserstein Training for Pose Estimation
2019
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Preserved Fulltext
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.
We also propose to construct the conservative target labels which model the inlier and outlier noises using a wrapped unimodal-uniform mixture distribution. ...
., pose/orientation estimation) in the context of deep learning. ...
We can sample K +1probabilities (i.e., 0 ≤ k ≤ K) on this PMF and followed by normalization for discrete unimodal probability distributions. ...
doi:10.1109/iccv.2019.00835
dblp:conf/iccv/LiuZCJDYK19
fatcat:xfp33xjnfrc2llx2udkpwbwole
Conservative Wasserstein Training for Pose Estimation
[article]
2019
arXiv
pre-print
Preserved Fulltext
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.
We also propose to construct the conservative target labels which model the inlier and outlier noises using a wrapped unimodal-uniform mixture distribution. ...
., pose/orientation estimation) in the context of deep learning. ...
We can sample K + 1 probabilities (i.e., 0 ≤ k ≤ K) on this PMF and followed by normalization for discrete unimodal probability distributions. ...
arXiv:1911.00962v1
fatcat:ypcbqpadtvhkpjsuqk7or3dkgi
« Previous
Showing results 1 — 15 out of 1,186 results