Home /
Research
Showing 499 - 504 / 904
Scaled-YOLOv4: Scaling Cross Stage Partial Network
Chien-YaoWang, AlexeyBochkovskiy, Hong-YuanMarkLiao....
Published date-11/16/2020
ObjectDetection, Real-TimeObjectDetection
We show that the YOLOv4 object detection neural network based on the CSP approach, scales both up and down and is applicable to small and large networks while maintaining optimal …
Combining GANs and AutoEncoders for Efficient Anomaly Detection
FabioCarrara, GiuseppeAmato, LucaBrombin....
Published date-11/16/2020
AdversarialAttack, AnomalyDetection, ImageClassification, UnsupervisedAnomalyDetection
In this work, we propose CBiGAN -- a novel method for anomaly detection in images, where a consistency constraint is introduced as a regularization term in both the encoder and …
Evaluating Sentence Segmentation and Word Tokenization Systems on Estonian Web Texts
KairitSirts, KairitPeekman....
Published date-11/16/2020
Tokenization
Texts obtained from web are noisy and do not necessarily follow the orthographic sentence and word boundary rules. Thus, sentence segmentation and word tokenization systems that have been developed on …
Quantum deep field: data-driven wave function, electron density generation, and atomization energy prediction and extrapolation with machine learning
MasashiTsubaki, TeruyasuMizoguchi....
Published date-11/16/2020
Deep neural networks (DNNs) have been used to successfully predict molecular properties calculated based on the Kohn--Sham density functional theory (KS-DFT). Although this prediction is fast and accurate, we believe …
Mixing ADAM and SGD: a Combined Optimization Method
NicolaLandro, IgnazioGallo, RiccardoLaGrassa....
Published date-11/16/2020
DocumentClassification
Optimization methods (optimizers) get special attention for the efficient training of neural networks in the field of deep learning. In literature there are many papers that compare neural models trained …
Overcomplete Deep Subspace Clustering Networks
JeyaMariaJoseValanarasu, VishalM.Patel....
Published date-11/16/2020
Clustering
Deep Subspace Clustering Networks (DSC) provide an efficient solution to the problem of unsupervised subspace clustering by using an undercomplete deep auto-encoder with a fully-connected layer to exploit the self …