Results 51 to 60 of about 60,104 (158)

Semantic Segmentation of Underwater Imagery Using Deep Networks Trained on Synthetic Imagery

Journal of Marine Science and Engineering, 2018
Recent breakthroughs in the computer vision community have led to the emergence of efficient deep learning techniques for end-to-end segmentation of natural scenes.
Michael O’Byrne, Vikram Pakrashi, Franck Schoefs, Bidisha Ghosh   +3 more
doaj   +1 more source

Human-like compositional learning of visually-grounded concepts using synthetic environments

CoRR
The compositional structure of language enables humans to decompose complex phrases and map them to novel visual concepts, showcasing flexible intelligence. While several algorithms exhibit compositionality, they fail to elucidate how humans learn to compose concept classes and ground visual cues through trial and error. To investigate this multi-modal
Zijun Lin, M. Ganesh Kumar, Cheston Tan
openaire   +2 more sources

Synthetic defect geometries of cast metal objects modeled via 2d Voronoi tessellations

Journal of Mathematics in Industry
In industry, defect detection is crucial for quality control. Non-destructive testing (NDT) methods are preferred as they do not influence the functionality of the object while inspecting. Automated defect detection is a growing field of research.
Natascha Jeziorski, Petra Gospodnetić, Claudia Redenbach   +2 more
doaj   +1 more source

Intrusion Detection Based on Adaptive Sample Distribution Dual-Experience Replay Reinforcement Learning

Mathematics
In order to cope with ever-evolving and increasing cyber threats, intrusion detection systems have become a crucial component of cyber security. Compared with signature-based intrusion detection methods, anomaly-based methods typically employ machine ...
Haonan Tan, Le Wang, Dong Zhu, Jianyu Deng   +3 more
doaj   +1 more source

Towards efficient and robust reinforcement learning via synthetic environments and offline data

, 2023
Over the past decade, Deep Reinforcement Learning (RL) has driven many advances in sequential decision-making, including remarkable applications in superhuman Go-playing, robotic control, and automated algorithm discovery. However, despite these successes, deep RL is also notoriously sample-inefficient, usually generalizes poorly to settings beyond the
openaire   +2 more sources

A methodological framework for evaluating ADASYN and borderline-SMOTE oversampling techniques in imbalanced epidemiological data: a proof-of-concept study for lassa fever detection

Recent Advances in Natural Sciences
Class imbalance in epidemiological datasets poses a fundamental challenge to developing accurate predictive models, particularly for rare but critical outcomes.
Osowomuabe Njama-Abang, Denis U. Ashishie, Paul T. Bukie, Ahena I. Bassey   +3 more
doaj   +1 more source

A Multi-Task Deep Learning Framework for Road Quality Analysis with Scene Mapping via Sim-to-Real Adaptation

Applied Sciences
Robust perception of road surface conditions is a critical challenge for the safe deployment of autonomous vehicles and the efficient management of transportation infrastructure.
Rahul Soans, Ryuichi Masuda, Yohei Fukumizu   +2 more
doaj   +1 more source

Shared Representation of SAR Target and Shadow Based on Multilayer Auto-encoder

Leida xuebao, 2013
Automatic Target Recognition (ATR) of Synthetic Aperture Radar (SAR) image is investigated. A SAR feature extraction algorithm based on multilayer auto-encoder is proposed.
Sun Zhi-jun, Xue Lei, Xu Yang-ming, Sun Zhi-yong   +3 more
doaj   +1 more source

Sim-Suction: Learning a Suction Grasp Policy for Cluttered Environments Using a Synthetic Benchmark

IEEE Transactions on Robotics
This paper presents Sim-Suction, a robust object-aware suction grasp policy for mobile manipulation platforms with dynamic camera viewpoints, designed to pick up unknown objects from cluttered environments. Suction grasp policies typically employ data-driven approaches, necessitating large-scale, accurately-annotated suction grasp datasets.
Juncheng Li 0010, David J. Cappelleri
openaire   +2 more sources

TC‐GEN: Data‐Driven Tropical Cyclone Downscaling Using Machine Learning‐Based High‐Resolution Weather Model

Journal of Advances in Modeling Earth Systems
Synthetic downscaling of tropical cyclones (TCs) is critically important to estimate the long‐term hazard of rare high‐impact storm events. Existing downscaling approaches rely on statistical or statistical‐deterministic models that are capable of ...
Renzhi Jing, Jianxiong Gao, Yunuo Cai, Dazhi Xi, Yinda Zhang, Yanwei Fu, Kerry Emanuel, Noah S. Diffenbaugh, Eran Bendavid   +8 more
doaj   +1 more source