7 citations · 13 across the 3 of their papers we have counts for
3 papers
cs.AR2025
GAVINA: flexible aggressive undervolting for bit-serial mixed-precision DNN acceleration
Jordi Fornt, Pau Fontova-Musté, Adrian Gras +5
Voltage overscaling, or undervolting, is an enticing approximate technique in the context of energy-efficient Deep Neural Network (DNN) acceleration, given the quadratic relationsh…
cs.AR2023★ 7 cited
An Automotive Case Study on the Limits of Approximation for Object Detection
Martí Caro, Hamid Tabani, Jaume Abella +9
The accuracy of camera-based object detection (CBOD) built upon deep learning is often evaluated against the real objects in frames only. However, such simplistic evaluation ignore…
cs.AR2023★ 6 cited
At-Scale Evaluation of Weight Clustering to Enable Energy-Efficient Object Detection
Martí Caro, Hamid Tabani, Jaume Abella
Accelerators implementing Deep Neural Networks for image-based object detection operate on large volumes of data due to fetching images and neural network parameters, especially if…