Search Results for author:
Found 4 papers, 3 papers with code
RATs-NAS: Redirection of Adjacent Trails on GCN for Neural Architecture Search
The RATs-NAS consists of two components: the Redirected Adjacent Trails GCN (RATs-GCN) and the Predictor-based Search Space Sampling (P3S) module.
Siamese-NAS: Using Trained Samples Efficiently to Find Lightweight Neural Architecture by Prior Knowledge
This idea causes it to surpass the current SOTA predictor on NASBench-201.
SFPN: Synthetic FPN for Object Detection
FPN (Feature Pyramid Network) has become a basic component of most SoTA one stage object detectors.
CSL-YOLO: A New Lightweight Object Detection System for Edge Computing
To reduce the computation cost, how to generate redundant features plays a significant role.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
