15 citations · 36 across the 10 of their papers we have counts for
11 papers
An automated approach for improving the inference latency and energy efficiency of pretrained CNNs by removing irrelevant pixels with focused convolutions
Caleb Tung, Nicholas Eliopoulos, Purvish Jajal +7
Computer vision often uses highly accurate Convolutional Neural Networks (CNNs), but these deep learning models are associated with ever-increasing energy and computation requireme…
Restructurable Activation Networks
Kartikeya Bhardwaj, James Ward, Caleb Tung +6
Is it possible to restructure the non-linear activation functions in a deep network to create hardware-efficient models? To address this question, we propose a new paradigm called…
Why Accuracy Is Not Enough: The Need for Consistency in Object Detection
Caleb Tung, Abhinav Goel, Fischer Bordwell +4
Object detectors are vital to many modern computer vision applications. However, even state-of-the-art object detectors are not perfect. On two images that look similar to human ey…
Irrelevant Pixels are Everywhere: Find and Exclude Them for More Efficient Computer Vision
Caleb Tung, Abhinav Goel, Xiao Hu +5
Computer vision is often performed using Convolutional Neural Networks (CNNs). CNNs are compute-intensive and challenging to deploy on power-contrained systems such as mobile and I…
Efficient Computer Vision on Edge Devices with Pipeline-Parallel Hierarchical Neural Networks
Abhinav Goel, Caleb Tung, Xiao Hu +3
Computer vision on low-power edge devices enables applications including search-and-rescue and security. State-of-the-art computer vision algorithms, such as Deep Neural Networks (…
Low-Power Multi-Camera Object Re-Identification using Hierarchical Neural Networks
Abhinav Goel, Caleb Tung, Xiao Hu +4
Low-power computer vision on embedded devices has many applications. This paper describes a low-power technique for the object re-identification (reID) problem: matching a query im…