Deep learning for visual understanding: A review

Y Guo, Y Liu, A Oerlemans, S Lao, S Wu, MS Lew - Neurocomputing, 2016 - Elsevier
Deep learning algorithms are a subset of the machine learning algorithms, which aim at
discovering multiple levels of distributed representations. Recently, numerous deep learning …

Computer vision for behaviour-based safety in construction: A review and future directions

W Fang, PED Love, H Luo, L Ding - Advanced Engineering Informatics, 2020 - Elsevier
The process of identifying and bringing to the fore people's unsafe behaviour is a core
function of implementing a behaviour-based safety (BBS) program in construction. This can …

A simple framework for contrastive learning of visual representations

T Chen, S Kornblith, M Norouzi… - … conference on machine …, 2020 - proceedings.mlr.press
This paper presents SimCLR: a simple framework for contrastive learning of visual
representations. We simplify recently proposed contrastive self-supervised learning …

Autoaugment: Learning augmentation strategies from data

ED Cubuk, B Zoph, D Mane… - Proceedings of the …, 2019 - openaccess.thecvf.com
Data augmentation is an effective technique for improving the accuracy of modern image
classifiers. However, current data augmentation implementations are manually designed. In …

[HTML][HTML] Albumentations: fast and flexible image augmentations

A Buslaev, VI Iglovikov, E Khvedchenya, A Parinov… - Information, 2020 - mdpi.com
Data augmentation is a commonly used technique for increasing both the size and the
diversity of labeled training sets by leveraging input transformations that preserve …

Ssd: Single shot multibox detector

W Liu, D Anguelov, D Erhan, C Szegedy… - Computer Vision–ECCV …, 2016 - Springer
We present a method for detecting objects in images using a single deep neural network.
Our approach, named SSD, discretizes the output space of bounding boxes into a set of …

Autoaugment: Learning augmentation policies from data

ED Cubuk, B Zoph, D Mane, V Vasudevan… - arxiv preprint arxiv …, 2018 - arxiv.org
In this paper, we take a closer look at data augmentation for images, and describe a simple
procedure called AutoAugment to search for improved data augmentation policies. Our key …

Deep learning with convolutional neural networks for EEG decoding and visualization

RT Schirrmeister, JT Springenberg… - Human brain …, 2017 - Wiley Online Library
Deep learning with convolutional neural networks (deep ConvNets) has revolutionized
computer vision through end‐to‐end learning, that is, learning from the raw data. There is …