Differentiable neural architecture search for sar image ship object detection

Li, Z.; Chen, L.; Huang, Xiaoshui; Zhang, Zhanwang; Shi, Haoqiang

doi:10.1049/icp.2021.0794

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As for manipulation of deformable elasto-plastic objects (dough, plasticine, etc. ), prior works propose to use either model-based (Cretu et al, 2011;Lin et al, 2022a;Matl and Bajcsy, 2021) or adaptive methods (NavarroAlarcon et al, 2016;Cherubini et al, 2020;Yoshimoto et al, 2011). As mentioned earlier, it is possible to leverage simulations as models for actual manipulation (Ganapathi et al, 2020).…”

Section: Manipulating Deformable Objectsmentioning

confidence: 99%

RoboCraft: Learning to see, simulate, and shape elasto-plastic objects in 3D with graph networks

Shi,

Xu,

Huang

et al. 2023

The International Journal of Robotics Research

View full text Add to dashboard Cite

Modeling and manipulating elasto-plastic objects are essential capabilities for robots to perform complex industrial and household interaction tasks (e.g., stuffing dumplings, rolling sushi, and making pottery). However, due to the high degrees of freedom of elasto-plastic objects, significant challenges exist in virtually every aspect of the robotic manipulation pipeline, for example, representing the states, modeling the dynamics, and synthesizing the control signals. We propose to tackle these challenges by employing a particle-based representation for elasto-plastic objects in a model-based planning framework. Our system, RoboCraft, only assumes access to raw RGBD visual observations. It transforms the sensory data into particles and learns a particle-based dynamics model using graph neural networks (GNNs) to capture the structure of the underlying system. The learned model can then be coupled with model predictive control (MPC) algorithms to plan the robot’s behavior. We show through experiments that with just 10 min of real-world robot interaction data, our robot can learn a dynamics model that can be used to synthesize control signals to deform elasto-plastic objects into various complex target shapes, including shapes that the robot has never encountered before. We perform systematic evaluations in both simulation and the real world to demonstrate the robot’s manipulation capabilities.

show abstract

Section: Manipulating Deformable Objectsmentioning

confidence: 99%

RoboCraft: Learning to see, simulate, and shape elasto-plastic objects in 3D with graph networks

Shi,

Xu,

Huang

et al. 2023

The International Journal of Robotics Research

View full text Add to dashboard Cite

show abstract

“…Moreover, designing novel NNs manually is becoming more and more difficult due to the limitation of existing knowledge. Therefore, in recent years, searching for a new great NN automatically has become a new popular research topic in the community of deep learning and artificial intelligence and obtained successful results in many fields, such as image classification [4], semantic segmentation [5], object detection [6], and natural language processing [7].…”

Section: Introductionmentioning

confidence: 99%

Scale adaptive fitness evaluation‐based particle swarm optimisation for hyperparameter and architecture optimisation in neural networks and deep learning

Wang

Chen

et al. 2022

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

Research into automatically searching for an optimal neural network (NN) by optimisation algorithms is a significant research topic in deep learning and artificial intelligence. However, this is still challenging due to two issues: Both the hyperparameter and architecture should be optimised and the optimisation process is computationally expensive. To tackle these two issues, this paper focusses on solving the hyperparameter and architecture optimization problem for the NN and proposes a novel light‐weight scale‐adaptive fitness evaluation‐based particle swarm optimisation (SAFE‐PSO) approach. Firstly, the SAFE‐PSO algorithm considers the hyperparameters and architectures together in the optimisation problem and therefore can find their optimal combination for the globally best NN. Secondly, the computational cost can be reduced by using multi‐scale accuracy evaluation methods to evaluate candidates. Thirdly, a stagnation‐based switch strategy is proposed to adaptively switch different evaluation methods to better balance the search performance and computational cost. The SAFE‐PSO algorithm is tested on two widely used datasets: The 10‐category (i.e., CIFAR10) and the 100−category (i.e., CIFAR100). The experimental results show that SAFE‐PSO is very effective and efficient, which can not only find a promising NN automatically but also find a better NN than compared algorithms at the same computational cost.

show abstract

Differentiable neural architecture search for sar image ship object detection

Cited by 2 publications

References 0 publications

RoboCraft: Learning to see, simulate, and shape elasto-plastic objects in 3D with graph networks

RoboCraft: Learning to see, simulate, and shape elasto-plastic objects in 3D with graph networks

Scale adaptive fitness evaluation‐based particle swarm optimisation for hyperparameter and architecture optimisation in neural networks and deep learning

Contact Info

Product

Resources

About