Compressed Object Detection

02/04/2021
by   Gedeon Muhawenayo, et al.
46

Deep learning approaches have achieved unprecedented performance in visual recognition tasks such as object detection and pose estimation. However, state-of-the-art models have millions of parameters represented as floats which make them computationally expensive and constrain their deployment on hardware such as mobile phones and IoT nodes. Most commonly, activations of deep neural networks tend to be sparse thus proving that models are over parametrized with redundant neurons. Model compression techniques, such as pruning and quantization, have recently shown promising results by improving model complexity with little loss in performance. In this work, we extended pruning, a compression technique that discards unnecessary model connections, and weight sharing techniques for the task of object detection. With our approach, we are able to compress a state-of-the-art object detection model by 30.0 loss in performance. We also show that our compressed model can be easily initialized with existing pre-trained weights, and thus is able to fully utilize published state-of-the-art model zoos.

READ FULL TEXT

page 1

page 2

page 3

research
10/07/2019

Deep Neural Network Compression for Image Classification and Object Detection

Neural networks have been notorious for being computationally expensive....
research
02/10/2021

Robustness in Compressed Neural Networks for Object Detection

Model compression techniques allow to significantly reduce the computati...
research
12/08/2020

The Lottery Ticket Hypothesis for Object Recognition

Recognition tasks, such as object recognition and keypoint estimation, h...
research
03/03/2023

R-TOSS: A Framework for Real-Time Object Detection using Semi-Structured Pruning

Object detectors used in autonomous vehicles can have high memory and co...
research
10/29/2020

Permute, Quantize, and Fine-tune: Efficient Compression of Neural Networks

Compressing large neural networks is an important step for their deploym...
research
02/27/2018

Recurrent Residual Module for Fast Inference in Videos

Deep convolutional neural networks (CNNs) have made impressive progress ...
research
01/04/2021

SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection

Deep learning based object detectors are commonly deployed on mobile dev...

Please sign up or login with your details

Forgot password? Click here to reset