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
Distribution-Based Invariant Deep Networks for Learning Meta-Features
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
Recent advances in deep learning from probability distributions successfully achieve classification or regression from distribution samples, thus invariant under permutation of the samples. ...
On both tasks, Dida learns meta-features supporting the characterization of a (labelled) dataset. ...
Distribution-Based Invariant Networks for Meta-Feature Learning This section describes the core of the proposed distribution-based invariant neural architectures, specifically the mechanism of mapping ...
arXiv:2006.13708v2
fatcat:rxqidzcapzbyhgzj56hsaoqxai
Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation
[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
representation on multiple "seen" domains, and (ii) meta-learning based cross-domain validation, which simulates train/test domain shift via applying meta-learning techniques in the training process. ...
In this paper, we propose Discriminative Adversarial Domain Generalization (DADG) with meta-learning-based cross-domain validation. ...
Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation thereon. 1 ...
arXiv:2011.00444v1
fatcat:odyqjjadrbdwvd46qbel4itoxa
Learning to Learn with Variational Information Bottleneck for Domain Generalization
[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.
We introduce a probabilistic meta-learning model for domain generalization, in which classifier parameters shared across domains are modeled as distributions. ...
To deal with domain shift, we learn domain-invariant representations by the proposed principle of meta variational information bottleneck, we call MetaVIB. ...
We introduce the IB principle for domain-invariant representation learning by a stochastic deep neural network. ...
arXiv:2007.07645v1
fatcat:m2l6kqyqwfdm5bdxrn5lajg7ia
Learning to Recommend via Meta Parameter Partition
[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.
The fixed part, capturing user invariant features, is shared by all users and is learned during offline meta learning stage. ...
The adaptive part, capturing user specific features, is learned during online meta learning stage. ...
Deep neural network (DNN) has potential to learn expressive features for accurate CTR prediction. CNN-based models [20] are biased to the interaction between neighboring features. ...
arXiv:1912.04108v1
fatcat:msk7xhsmbrebliak6vp3lwrzyy
Cross Domain Adaptation of Crowd Counting with Model-Agnostic Meta-Learning
2021
Applied Sciences
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 the domain adaptation in feature extraction, we propose an adaptive domain-invariant feature extracting module. ...
CNN-based crowd-counting algorithms usually consist of feature extraction, density estimation, and count regression. ...
Deep convolutional networks first extract feature maps from images and the density value of each feature pixel is then predicted. ...
doi:10.3390/app112412037
fatcat:l6lqcpggzbadrhfrhexkyzdlwa
An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Dataset
[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.
The standard benchmarks in meta-learning are challenged by learning on diverse task distributions. ...
In this model, the learnable regularization function contains a task-invariant common feature encoder and task-specific learner represented by a shallow network. ...
In Section 2, we introduce some related work for both optimization-based meta-learning and deep unrolled networks for MRI reconstructions. ...
arXiv:2110.00715v1
fatcat:bp7z3qyajzcofi5nujekpq76vu
A Bit More Bayesian: Domain-Invariant Learning with Uncertainty
[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
Ablation studies validate the synergistic benefits of our Bayesian treatment when jointly learning domain-invariant representations and classifiers for domain generalization. ...
In this paper, we address both challenges with a probabilistic framework based on variational Bayesian inference, by incorporating uncertainty into neural network weights. ...
Acknowledgements This work is financially supported by the Inception Institute of Artificial Intelligence, the University of Amsterdam and the allowance Top consortia for Knowledge and Innovation (TKIs ...
arXiv:2105.04030v3
fatcat:wetgafpoqraqzmx5lchblqzldq
Knowledge as Invariance – History and Perspectives of Knowledge-augmented Machine 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.
Major weaknesses of present-day deep learning models are, for instance, their lack of adaptability to changes of environment or their incapability to perform other kinds of tasks than the one they were ...
trained for. ...
Weight sharing in convolutional layers of deep networks without doubt provides a strong prior for the most common deep learning applications [74] . ...
arXiv:2012.11406v1
fatcat:nnbnsrwfr5fbxg4qj3a4cfajk4
Domain Generalization with Optimal Transport and 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
Previous domain generalization approaches mainly focused on learning invariant features and stacking the learned features from each source domain to generalize to a new target domain while ignoring the ...
For this, one possible solution is to constrain the label-similarity when extracting the invariant features and to take advantage of the label similarities for class-specific cohesion and separation of ...
[24] proposed an end-to-end deep domain generalization approach by leveraging deep neural networks for domain-invariant representation learning. ...
arXiv:2007.10573v1
fatcat:kqubwtaw5nf3hpvct6s5ey3hru
Meta-Learning Dynamics Forecasting Using Task Inference
[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
Current deep learning models for dynamics forecasting struggle with generalization. ...
We propose a model-based meta-learning method called DyAd which can generalize across heterogeneous domains by partitioning them into different tasks. ...
DyAd: Dynamic Adaptation Network We propose a model-based meta-learning approach for dynamics forecasting. ...
arXiv:2102.10271v3
fatcat:vqvloatadrgdneyrcmfgmdnv2y
Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning
[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
Instead, we think a local descriptor based image-to-class measure should be taken, inspired by its surprising success in the heydays of local invariant features. ...
The proposed DN4 not only learns the optimal deep local descriptors for the image-to-class measure, but also utilizes the higher efficiency of such a measure in the case of example scarcity, thanks to ...
Meta-learning based methods. ...
arXiv:1903.12290v2
fatcat:yrft43dj2rbcpbvarsjdpm4uv4
Robust Compare Network for Few-Shot Learning
2020
IEEE Access
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.
As illustrated in Fig. 2 , our method is composed of three key modules: (1) Embedding module: a deep neural network with shift-invariant blocks and a self-attention block to learn invariance visual features ...
On the other hand, some FSL approaches based on meta-learning follow the key idea of learning-tolearn mechanism. ...
doi:10.1109/access.2020.3012720
fatcat:kwgz35ngsrdbbgfg2y46gqfjpm
An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Dataset
2021
Journal of Imaging
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.
We partition these network parameters into two parts: a task-invariant part for the common feature encoder component of the regularization, and a task-specific part to account for the variations in the ...
In this model, the nonconvex nonsmooth regularization term is parameterized as a structured deep network where the network parameters can be learned from data. ...
In Section 2, we discuss related work for both optimization-based meta-learning and deep unrolled networks for MRI reconstructions. ...
doi:10.3390/jimaging7110231
pmid:34821862
pmcid:PMC8621471
fatcat:attame2j5rg2jef3uodbarw7xm
Learning to Warm-Start Bayesian Hyperparameter Optimization
[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 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To this end, we introduce a Siamese network composed of deep feature and meta-feature extractors, where deep feature extractor provides a semantic representation of each instance in a dataset and meta-feature ...
In this paper, we propose deep metric learning to learn meta-features over datasets such that the similarity over them is effectively measured by Euclidean distance between their associated meta-features ...
Feature Extractors Setup To learn a distance function using Siamese network, the network composed of deep feature extractor and meta-feature extractor are used as a wing of Siamese network. ...
arXiv:1710.06219v3
fatcat:nqd3zduti5aehakgnfehbmqghe
Exploiting Domain-Specific Features to Enhance Domain Generalization
[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.
Our key insight is to disentangle features in the latent space while jointly learning both domain-invariant and domain-specific features in a unified framework. ...
The domain-specific representation is optimized through the meta-learning framework to adapt from source domains, targeting a robust generalization on unseen domains. ...
Distributionally
robust neural networks for group shifts: On the importance of regularization for worst-case
generalization, 2020. ...
arXiv:2110.09410v1
fatcat:koqcioubtvdk7ouacwsu3xi2he
« Previous
Showing results 1 — 15 out of 12,216 results