A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Filters
Large-Scale Distance Metric Learning with Uncertainty
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Preserved Fulltext
Most of the existing methods propose to learn a distance metric with pairwise or triplet constraints. ...
Distance metric learning (DML) has been studied extensively in the past decades for its superior performance with distance-based algorithms. ...
It indicates that latent examples with low uncertainty are more appropriate for the large-scale data set as the reference points. ...
doi:10.1109/cvpr.2018.00891
dblp:conf/cvpr/QianTLZJ18
fatcat:fbpgqfyyqja7njxvdcuyz6kfqq
Large-scale Distance Metric Learning with Uncertainty
[article]
2018
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 2019; you can also visit the original URL.
The file type is application/pdf.
Most of the existing methods propose to learn a distance metric with pairwise or triplet constraints. ...
Distance metric learning (DML) has been studied extensively in the past decades for its superior performance with distance-based algorithms. ...
It indicates that latent examples with low uncertainty are more appropriate for the large-scale data set as the reference points. ...
arXiv:1805.10384v1
fatcat:msmn5l4bxfhahdny7knpjjjime
Meta-Learned Confidence for Few-shot Learning
[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
We validate our few-shot learning model with meta-learned confidence on four benchmark datasets, on which it largely outperforms strong recent baselines and obtains new state-of-the-art results. ...
We achieve this by meta-learning an input-adaptive distance metric over a task distribution under various model and data perturbations, which will enforce consistency on the model predictions under diverse ...
We see that the PN with metric scaling underperforms the plain PN with Euclidean distance. ...
arXiv:2002.12017v2
fatcat:iizg5agw2zexhaxfs3vip4ackq
MetaCVR: Conversion Rate Prediction via Meta Learning in Small-Scale Recommendation Scenarios
[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
Subsequently, a Distance Metric Network (DMN) is devised to calculate the distance metrics between each sample and all prototypes to facilitate mitigating the distribution uncertainty. ...
Different from large-scale platforms such as Taobao and Amazon, CVR modeling in small-scale recommendation scenarios is more challenging due to the severe Data Distribution Fluctuation (DDF) issue. ...
Metric Network In metric-based meta learning, the choice of distance metric is crucial. ...
arXiv:2112.13753v4
fatcat:u3st3d3rhrc2xm7arvz5d3qwfu
Mitigating Uncertainty in Document Classification
2019
Proceedings of the 2019 Conference of the North
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 design a metric learning method on feature representations, which can boost the performance of dropout-based uncertainty methods with smaller prediction variance in accurate prediction trials. ...
returned by machine learning models. ...
Most existing uncertainty models are based on Bayesian models, which are not only timeconsuming but also unable to handle large-scale data sets. ...
doi:10.18653/v1/n19-1316
dblp:conf/naacl/ZhangCLR19
fatcat:ylkundijqzdffbvzua7yxayj5u
Perception Score, A Learned Metric for Open-ended Text Generation Evaluation
[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
Existing metrics such as BLEU show a low correlation with human judgment. We propose a novel and powerful learning-based evaluation metric: Perception Score. ...
Moreover, it also shows the amount of uncertainty about its evaluation result. By connecting the uncertainty, Perception Score gives a more accurate evaluation for the generation system. ...
Uncertainty comes with judgment. ...
arXiv:2008.03082v2
fatcat:sgjbrr6w4vanjc6x7yifde42s4
Active learning for large multi-class problems
2009
2009 IEEE Conference on Computer Vision and 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 2010; you can also visit the original URL.
The file type is application/pdf.
Scarcity and infeasibility of human supervision for large scale multi-class classification problems necessitates active learning. ...
Unfortunately, existing active learning methods for multi-class problems are inherently binary methods and do not scale up to a large number of classes. ...
Recent methods in metric learning learns a distance metric parameterized by a Mahalanobis metric that is consistent with the training data [1, 5, 20, 8] . ...
doi:10.1109/cvpr.2009.5206651
dblp:conf/cvpr/JainK09
fatcat:sn5s2wvyxjb2bamvnkti7emngi
Only Bayes should learn a manifold (on the estimation of differential geometric structure from data)
[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
To properly learn the differential geometric structure, non-probabilistic methods must apply regularizations that enforce large gradients, which go against common wisdom. ...
We investigate learning of the differential geometric structure of a data manifold embedded in a high-dimensional Euclidean space. ...
Also note that scaling Σ also scales the expected distance: very uncertain metrics imply large expected distances. ...
arXiv:1806.04994v3
fatcat:qhysomkjbjgnfdr6tqmfkjh47e
Active learning for large multi-class problems
2009
2009 IEEE Conference on Computer Vision and 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 2010; you can also visit the original URL.
The file type is application/pdf.
Scarcity and infeasibility of human supervision for large scale multi-class classification problems necessitates active learning. ...
Unfortunately, existing active learning methods for multi-class problems are inherently binary methods and do not scale up to a large number of classes. ...
Recent methods in metric learning learns a distance metric parameterized by a Mahalanobis metric that is consistent with the training data [1, 5, 20, 8] . ...
doi:10.1109/cvprw.2009.5206651
fatcat:uw25r5zxqvgsjjnpnqbug5fm6a
Randomised Gaussian Process Upper Confidence Bound for Bayesian Optimisation
2020
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
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.
with large incremental batches. ...
Deep metric learning with 3 standard AL heuristics (uncertainty (US), expected gradient length (EGL), model output change (MOC)) all outperform random sampling (RND) when triplets are added one at a time ...
doi:10.24963/ijcai.2020/312
dblp:conf/ijcai/KumariGCC20
fatcat:t6l6srkcufe5bihmudcgs4fazu
Parcel-Based Active Learning for Large Extent Cultivated Area Mapping
2018
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
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 2019; you can also visit the original URL.
The file type is application/pdf.
This paper focuses on agricultural land cover mapping at a high resolution scale and over large areas from an operational point of view and from a high-resolution monodate image. ...
processed at parcel scale. ...
MAO is not effective with a multi-class problem. Thus the kept distance-based metric is Mahalanobis distance [26] although is it parametric. ...
doi:10.1109/jstars.2017.2751148
fatcat:ykkwbtlg5bfjjokfzuvmg6xsli
Absolute geo-localization thanks to Hidden Markov Model and exemplar-based metric learning
2015
2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
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 2017; you can also visit the original URL.
The file type is application/pdf.
To achieve this goal, we define some constraints so that the distance between a database image and a query image representing the same scene is smaller than the distance between this query image and other ...
This paper addresses the problem of absolute visual ego-localization of an autonomous vehicle equipped with a monocular camera that has to navigate in an urban environment. ...
leading to an exemplar-based metric learning scheme. ...
doi:10.1109/cvprw.2015.7301394
dblp:conf/cvpr/BarzTCHS15
fatcat:iqaxko2jkvcdjkwo6vang64bte
STUN: Self-Teaching Uncertainty Estimation for Place 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.
To this end, we first train a teacher net using a standard metric learning pipeline to produce embedding priors. ...
Our experimental results on the large-scale Pittsburgh30k dataset demonstrate that STUN outperforms the state-of-the-art methods in both recognition accuracy and the quality of uncertainty estimation. ...
This limitation makes classification based place recognition impractical for real-world large scale applications. Thus, in this study, we only focus on metric learning based place recognition. ...
arXiv:2203.01851v1
fatcat:7kwmog5f3fffrads64cvx6bf7a
Elliptical Ordinal Embedding
[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 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Typically, each object is mapped onto a point vector in a low dimensional metric space. ...
In addition, we illustrate the merit of modelling uncertainty, which enriches the visual perception of the mapped objects in the space. ...
Moreover, these methods rely on expensive gradient projections and do not easily scale to large datasets. ...
arXiv:2105.10457v2
fatcat:b62rf5kgu5fjzdxubhc5lq5npi
Batch Decorrelation for Active Metric Learning
[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
We present an active learning strategy for training parametric models of distance metrics, given triplet-based similarity assessments: object x_i is more similar to object x_j than to x_k. ...
In contrast to prior work on class-based learning, where the fundamental goal is classification and any implicit or explicit metric is binary, we focus on perceptual metrics that express the degree of ...
with large incremental batches. ...
arXiv:2005.10008v2
fatcat:5dacudmo25didelhmaav2peo3m
« Previous
Showing results 1 — 15 out of 72,953 results