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
Explainable Abstract Trains Dataset
[article]
2020
arXiv
pre-print
Preserved Fulltext
The Explainable Abstract Trains Dataset is an image dataset containing simplified representations of trains. ...
The dataset is accompanied by an ontology that conceptualizes and classifies the depicted trains based on their visual characteristics, allowing for a precise understanding of how each train was labeled ...
In
Yoshua Bengio and Yann LeCun, editors, 2nd International Conference on Learn-
ing Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Workshop
Track Proceedings, 2014.
8. ...
arXiv:2012.12115v1
fatcat:deixf5bzajf2rnktjk36q2rwhm
Score-Based Generative Classifiers
[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
Generative models have been used as adversarially robust classifiers on simple datasets such as MNIST, but this robustness has not been observed on more complex datasets like CIFAR-10. ...
Nevertheless, we find that these models are only slightly, if at all, more robust than discriminative baseline models on out-of-distribution tasks based on common image corruptions. ...
In Yoshua Bengio and
Yann LeCun, editors, 2nd International Conference on Learning Representations, ICLR 2014,
Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings, 2014.
[45] Sasha ...
arXiv:2110.00473v2
fatcat:6yer6cgkxnbf7kg2m2xmxjtre4
PARL: Enhancing Diversity of Ensemble Networks to Resist Adversarial Attacks via Pairwise Adversarially Robust Loss Function
[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 security of Deep Learning classifiers is a critical field of study because of the existence of adversarial attacks. ...
Such attacks usually rely on the principle of transferability, where an adversarial example crafted on a surrogate classifier tends to mislead the target classifier trained on the same dataset even if ...
In 2nd International
Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014,
Conference Track Proceedings, 2014. ...
arXiv:2112.04948v1
fatcat:i7ab4hvgprcgvdpnowrlwmaiwa
Variational Neural Machine Translation with Normalizing Flows
[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.
Unfortunately, learning informative latent variables is non-trivial, as the latent space can be prohibitively large, and the latent codes are prone to be ignored by many translation models at training ...
Variational Neural Machine Translation (VNMT) is an attractive framework for modeling the generation of target translations, conditioned not only on the source sentence but also on some latent random variables ...
In 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings. ...
arXiv:2005.13978v1
fatcat:7ysqtt4kgzgm3l4kddct7byihy
Invertible generative models for inverse problems: mitigating representation error and dataset bias
[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 additionally compare performance for compressive sensing to unlearned methods, such as the deep decoder, and we establish theoretical bounds on expected recovery error in the case of a linear invertible ...
In this paper, we demonstrate that invertible neural networks, which have zero representation error by design, can be effective natural signal priors at inverse problems such as denoising, compressive ...
(eds.), 2nd Interna-
tional Conference on Learning Representations, ICLR
2014, Banff, AB, Canada, April 14-16, 2014, Conference
Track Proceedings, 2014.
Liu, Z., Luo, P., Wang, X., and Tang, X. ...
arXiv:1905.11672v4
fatcat:hgpfoh6frfa4thyxvhmqjzqomi
Variational Tracking and Prediction with Generative Disentangled State-Space Models
[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.
Generative and inference model are jointly learned from observations only. ...
Tracking performance is increased significantly over prior art. ...
In: 2nd International
Conference on Learning Representations, ICLR 2014,
Banff, AB, Canada, April 14-16, 2014, Conference
Track Proceedings. u r l: http://arxiv.org/abs/
1312.6114. ...
arXiv:1910.06205v1
fatcat:7radjf2djnfh7copebflvopid4
PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation
[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.
Moreover, our method achieves considerable performance in classifying out-of-the training distribution samples, evaluated on Cityscapes to KITTI dataset. ...
The extensive experiments on Cityscapes and CamVid benchmarks demonstrate that our method significantly outperforms baselines in capturing small classes and in few-data regimes. ...
In 2nd International Conference
on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference
Track Proceedings, 2014.
[62] Sergey Ioffe and Christian Szegedy. ...
arXiv:2109.10083v1
fatcat:4zzppv7iuzelxiqu2i6h5fdiey
What to Pre-Train on? Efficient Intermediate Task Selection
[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
Our results show that efficient embedding based methods that rely solely on the respective datasets outperform computational expensive few-shot fine-tuning approaches. ...
similar sequential fine-tuning gains can be achieved in adapter settings, and subsequently consolidate previously proposed methods that efficiently identify beneficial tasks for intermediate transfer learning ...
We thank Leonardo Ribeiro and the anonymous reviewers for insightful feedback and suggestions on a draft of this paper. ...
arXiv:2104.08247v2
fatcat:4ljcfshev5f3tmgugrrrkh3s4m
A Survey of Deep Active Learning
[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
Deep learning (DL) is greedy for data and requires a large amount of data supply to optimize massive parameters, so that the model learns how to extract high-quality features. ...
A natural idea is whether AL can be used to reduce the cost of sample annotations, while retaining the powerful learning capabilities of DL. Therefore, deep active learning (DAL) has emerged. ...
In 2nd International Conference on
Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings.
[115] Andreas Kirsch, Joost van Amersfoort, and Yarin Gal ...
arXiv:2009.00236v2
fatcat:zuk2doushzhlfaufcyhoktxj7e
Neural Network Module Decomposition and Recomposition
[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 2022; you can also visit the original URL.
The file type is application/pdf.
In contrast to existing studies based on reusing models that involve retraining, such as a transfer learning model, the proposed method does not require retraining and has wide applicability as it can ...
To extract modules, we designed a learning method and a loss function to maximize shared weights among modules. ...
A review of modularization Canada, April 14-16, 2014, Conference Track Proceedings.
techniques in artificial neural networks. ...
arXiv:2112.13208v1
fatcat:zcccxh6nmrberacsaj3b5ct4vi
Towards Robust Explanations for Deep Neural Networks
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 2021; you can also visit the original URL.
The file type is application/pdf.
We develop a unified theoretical framework for deriving bounds on the maximal manipulability of a model. ...
Explanation methods shed light on the decision process of black-box classifiers such as deep neural networks. But their usefulness can be compromised because they are susceptible to manipulations. ...
In 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Workshop Track Proceedings, 2014. [3] Matthew D. Zeiler and Rob Fergus. ...
doi:10.1016/j.patcog.2021.108194
fatcat:qv77e5cilzfudkd2dcce3fkgsy
Improving Neural Topic Models using Knowledge Distillation
[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.
In 2nd International
Conference on Learning Representations, ICLR
2014, Banff, AB, Canada, April 14-16, 2014, Con-
ference Track Proceedings.
Thomas K. Landauer and Susan T. Dumais. 1997. ...
In 1st International Con-
ference on Learning Representations, ICLR 2013,
Scottsdale, Arizona, USA, May 2-4, 2013, Workshop
Track Proceedings. ...
arXiv:2010.02377v1
fatcat:xm7rr7hw7nc6nngheo4x5t6ncu
When are Non-Parametric Methods Robust?
[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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2003.06121v1 fatcat:rnzm5pb2vbgnxpekp2s3ycdytq
In 2nd International Confer-
ence on Learning Representations, ICLR 2014, Banff, AB,
Canada, April 14-16, 2014, Conference Track Proceed-
ings, 2014.
Wang, Y., Jha, S., and Chaudhuri, K. ...
In 6th International Conference on
Learning Representations, ICLR 2018, Vancouver, BC,
Canada, April 30 -May 3, 2018, Conference Track Pro-
ceedings, 2018. ...
Therefore one must have cardinality at least |S| 2 , which implies the same about |S r |. Proof. ...
arXiv:2003.06121v2
fatcat:jz2a2oadoffxtg4ph7hsqq6vc4
Transforming Gaussian Processes With Normalizing Flows
[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:2011.01596v1 fatcat:77jpyfcb25bhfnam4athprzkum
The resulting algorithm's computational and inferential performance is excellent, and we demonstrate this on a range of data sets. ...
Inspired by the growing body of work on Normalizing Flows, we enlarge this class of priors through a parametric invertible transformation that can be made input-dependent. ...
In 2nd International Conference
on Learning Representations, ICLR 2014, Banff,
AB, Canada, April 14-16, 2014, Conference Track
Proceedings. ...
arXiv:2011.01596v2
fatcat:njvhgcnpjbfo3oeojxg4icryzu
Beyond Robustness: Resilience Verification of Tree-Based Classifiers
[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.
In this paper we criticize the robustness measure traditionally employed to assess the performance of machine learning models deployed in adversarial settings. ...
To mitigate the limitations of robustness, we introduce a new measure called resilience and we focus on its verification. ...
CoRR, abs/2004.03295, 2020. Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings,
[5] Stefano Calzavara, Claudio Lucchese, and Gabriele Tolomei. ...
arXiv:2112.02705v1
fatcat:ahw6lbkf7fbnnlubo7z5zuq4wy
« Previous
Showing results 1 — 15 out of 26 results