In this paper, we propose to reduce power consumption of YOLOv5 DNN architecture. We decided to use compressed convolutional technique, transfer learning, ...

Improving the Energy Efficiency of Real-time DNN Object Detection via Compression, Transfer Learning, and Scale Prediction. October 2022. DOI:10.1109/NAS55553 ...

Improving the energy efficiency of real-time DNN object detection via compression, transfer learning, and scale prediction. D Biswas, MMM Rahman, Z Zong, J ...

Zong and J. Tešić, “Improving the Energy Efficiency of Real-time DNN Object Detection via Compression, Transfer Learning, and Scale Prediction,” 2022 IEEE ...

(2022). Improving the Energy Efficiency of Real-time DNN Object Detection via Compression, Transfer Learning, and Scale Prediction. IEEE. View all ...

We developed a novel dataset by training convolutional neural networks in 12 different computer vision datasets and applying runtime decisions.

Jul 25, 2024 · Thus, the proposed approach allows compressing the neural network, to reduce the energy consumption while keeping very good prediction ...

We decided to use compressed convolutional technique, transfer learning, backbone shrinkage, and scale prediction to reduce the number of ...

A collection of recent methods on DNN compression and acceleration. There are mainly 5 kinds of methods for efficient DNNs: neural architecture re-design or ...

Nov 2, 2023 · (2022) Improving the energy efficiency of real-time DNN object detection via compression, transfer learning, and scale prediction. 2022 IEEE ...