Showing cs.CVShow all
2 papers · 1 filter
cs.CV2019
Dataset Culling: Towards Efficient Training Of Distillation-Based Domain Specific Models
Kentaro Yoshioka, Edward Lee, Simon Wong +1
Real-time CNN-based object detection models for applications like surveillance can achieve high accuracy but are computationally expensive. Recent works have shown 10 to 100x reduc…
cs.CV2018
Training Domain Specific Models for Energy-Efficient Object Detection
Kentaro Yoshioka, Edward Lee, Mark Horowitz
We propose an end-to-end framework for training domain specific models (DSMs) to obtain both high accuracy and computational efficiency for object detection tasks. DSMs are trained…