paper-with-me

Papers

Dropout as data augmentation

2015-06-29 · Xavier Bouthillier, Kishore Konda, Pascal Vincent, Roland Memisevic

Dropout is typically interpreted as bagging a large number of models sharing parameters. We show that using dropout in a network can also be interpreted as a kind of data augmentation in the input space without domain knowledge. We present an approach to projecting the dropout noise within a network back into the input space, thereby generating augmented versions of the training data, and we show that training a deterministic network on the augmented samples yields similar results. Finally, we propose a new dropout noise scheme based on our observations and show that it improves dropout results without adding significant computational cost.

📄 PDF Abstract BibTeX arXiv:1506.08700

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

The Penalty Imposed by Ablated Data Augmentation

2020-06-08 · Frederick Liu, Amir Najmi, Mukund Sundararajan

There is a set of data augmentation techniques that ablate parts of the input at random. These include input dropout, cutout, and random erasing. We term these techniques ablated data augmentation. Though these technique…

Data Augmentation

Data augmentation instead of explicit regularization

2018-06-11 · ICLR 2018 1 · Alex Hernández-García, Peter König

Contrary to most machine learning models, modern deep artificial neural networks typically include multiple components that contribute to regularization. Despite the fact that some (explicit) regularization techniques, s…

Data AugmentationObject Categorization

Dropout Training for SVMs with Data Augmentation

2015-08-10 · Ning Chen, Jun Zhu, Jianfei Chen, Ting Chen

Dropout and other feature noising schemes have shown promising results in controlling over-fitting by artificially corrupting the training data. Though extensive theoretical and empirical studies have been performed for …

Data AugmentationRepresentation Learning

Tackling Occlusion in Siamese Tracking with Structured Dropouts

2020-06-30 · Deepak K. Gupta, Efstratios Gavves, Arnold W. M. Smeulders

Occlusion is one of the most difficult challenges in object tracking to model. This is because unlike other challenges, where data augmentation can be of help, occlusion is hard to simulate as the occluding object can be…

Data AugmentationObject Tracking

Adjusting for Dropout Variance in Batch Normalization and Weight Initialization

2016-07-08 · Dan Hendrycks, Kevin Gimpel

We show how to adjust for the variance introduced by dropout with corrections to weight initialization and Batch Normalization, yielding higher accuracy. Though dropout can preserve the expected input to a neuron between…

Data Augmentation