AutoSegEdge: Searching for the edge device real-time semantic segmentation based on multi-task learning
Z Dou, D Ye, B Wang - Image and Vision Computing, 2023 - Elsevier
Real-time semantic segmentation is a challenging task for resource-constrained edge
devices. We propose AutoSegEdge, based on Neural Architecture Search (NAS), a …
devices. We propose AutoSegEdge, based on Neural Architecture Search (NAS), a …
EBNAS: Efficient binary network design for image classification via neural architecture search
C Shi, Y Hao, G Li, S Xu - Engineering Applications of Artificial Intelligence, 2023 - Elsevier
Abstract To deploy Convolutional Neural Networks (CNNs) on resource-limited devices,
binary CNNs with 1-bit activations and weights prove to be a promising approach …
binary CNNs with 1-bit activations and weights prove to be a promising approach …
ASMEvoNAS: Adaptive segmented multi-objective evolutionary network architecture search
Network architecture search (NAS) has attracted much attention as an automatic design
technique of network architecture. In particular, multi-objective evolutionary algorithms …
technique of network architecture. In particular, multi-objective evolutionary algorithms …
Large-scale aerial scene perception based on self-supervised multi-view stereo via cycled generative adversarial network
KW Tong, Z Shi, GY Zhu, Y Duan, Y Hou, EQ Wu… - Information …, 2024 - Elsevier
Unmanned aerial vehicle (UAV) has the characteristics of strong maneuverability and wide
field of vision, and its application in real-time terrain perception and target capture is one of …
field of vision, and its application in real-time terrain perception and target capture is one of …
PSO-based lightweight neural architecture search for object detection
T Gong, Y Ma - Swarm and Evolutionary Computation, 2024 - Elsevier
Abstract In recent years, Neural Architecture Search (NAS) has received widespread
attention for its remarkable ability to design neural networks. However, existing NAS works …
attention for its remarkable ability to design neural networks. However, existing NAS works …
Tas: ternarized neural architecture search for resource-constrained edge devices
Ternary Neural Networks (TNNs) compress network weights and activation functions into 2-
bit representation resulting in remarkable network compression and energy efficiency …
bit representation resulting in remarkable network compression and energy efficiency …
A fast evolutionary knowledge transfer search for multiscale deep neural architecture
The emergence of neural architecture search (NAS) algorithms has removed the constraints
on manually designed neural network architectures, so that neural network development no …
on manually designed neural network architectures, so that neural network development no …
DASS: differentiable architecture search for sparse neural networks
The deployment of Deep Neural Networks (DNNs) on edge devices is hindered by the
substantial gap between performance requirements and available computational power …
substantial gap between performance requirements and available computational power …
Learning activation functions for adversarial attack resilience in cnns
Adversarial attacks on convolutional neural networks (CNNs) have been a serious concern
in recent years, as they can cause CNNs to produce inaccurate predictions. Through our …
in recent years, as they can cause CNNs to produce inaccurate predictions. Through our …
AutoGAN-DSP: Stabilizing GAN architecture search with deterministic score predictors
H Jo, C Joo - Neurocomputing, 2024 - Elsevier
Abstract Generative Adversarial Network (GAN) has been widely used in many research
areas of computer vision, anomaly detection, translation, optimal control, etc. However, in …
areas of computer vision, anomaly detection, translation, optimal control, etc. However, in …