Domain Specific Approximation for Object Detection

10/04/2018
by   Ting-Wu Chin, et al.
0

There is growing interest in object detection in advanced driver assistance systems and autonomous robots and vehicles. To enable such innovative systems, we need faster object detection. In this work, we investigate the trade-off between accuracy and speed with domain-specific approximations, i.e. category-aware image size scaling and proposals scaling, for two state-of-the-art deep learning-based object detection meta-architectures. We study the effectiveness of applying approximation both statically and dynamically to understand the potential and the applicability of them. By conducting experiments on the ImageNet VID dataset, we show that domain-specific approximation has great potential to improve the speed of the system without deteriorating the accuracy of object detectors, i.e. up to 7.5x speedup for dynamic domain-specific approximation. To this end, we present our insights toward harvesting domain-specific approximation as well as devise a proof-of-concept runtime, AutoFocus, that exploits dynamic domain-specific approximation.

READ FULL TEXT

page 4

page 5

02/08/2019

AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling

In vision-enabled autonomous systems such as robots and autonomous cars,...
11/11/2019

Draw This Object: A Study of Debugging Representations

Domain-specific debugging visualizations try to provide a view of a runt...
02/01/2019

Dataset Culling: Towards Efficient Training Of Distillation-Based Domain Specific Models

Real-time CNN based object detection models for applications like survei...
11/06/2018

Training Domain Specific Models for Energy-Efficient Object Detection

We propose an end-to-end framework for training domain specific models (...
08/15/2021

Vector-Decomposed Disentanglement for Domain-Invariant Object Detection

To improve the generalization of detectors, for domain adaptive object d...
03/22/2022

Gated Domain-Invariant Feature Disentanglement for Domain Generalizable Object Detection

For Domain Generalizable Object Detection (DGOD), Disentangled Represent...
02/11/2021

ABOShips – An Inshore and Offshore Maritime Vessel Detection Dataset with Precise Annotations

Availability of domain-specific datasets is an essential problem in obje...