Cargando…
Investigating the Potential of Network Optimization for a Constrained Object Detection Problem
Object detection models are usually trained and evaluated on highly complicated, challenging academic datasets, which results in deep networks requiring lots of computations. However, a lot of operational use-cases consist of more constrained situations: they have a limited number of classes to be d...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8321328/ https://www.ncbi.nlm.nih.gov/pubmed/34460514 http://dx.doi.org/10.3390/jimaging7040064 |
_version_ | 1783730825791012864 |
---|---|
author | Ophoff, Tanguy Gullentops, Cédric Van Beeck, Kristof Goedemé, Toon |
author_facet | Ophoff, Tanguy Gullentops, Cédric Van Beeck, Kristof Goedemé, Toon |
author_sort | Ophoff, Tanguy |
collection | PubMed |
description | Object detection models are usually trained and evaluated on highly complicated, challenging academic datasets, which results in deep networks requiring lots of computations. However, a lot of operational use-cases consist of more constrained situations: they have a limited number of classes to be detected, less intra-class variance, less lighting and background variance, constrained or even fixed camera viewpoints, etc. In these cases, we hypothesize that smaller networks could be used without deteriorating the accuracy. However, there are multiple reasons why this does not happen in practice. Firstly, overparameterized networks tend to learn better, and secondly, transfer learning is usually used to reduce the necessary amount of training data. In this paper, we investigate how much we can reduce the computational complexity of a standard object detection network in such constrained object detection problems. As a case study, we focus on a well-known single-shot object detector, YoloV2, and combine three different techniques to reduce the computational complexity of the model without reducing its accuracy on our target dataset. To investigate the influence of the problem complexity, we compare two datasets: a prototypical academic (Pascal VOC) and a real-life operational (LWIR person detection) dataset. The three optimization steps we exploited are: swapping all the convolutions for depth-wise separable convolutions, perform pruning and use weight quantization. The results of our case study indeed substantiate our hypothesis that the more constrained a problem is, the more the network can be optimized. On the constrained operational dataset, combining these optimization techniques allowed us to reduce the computational complexity with a factor of 349, as compared to only a factor 9.8 on the academic dataset. When running a benchmark on an Nvidia Jetson AGX Xavier, our fastest model runs more than 15 times faster than the original YoloV2 model, whilst increasing the accuracy by 5% Average Precision (AP). |
format | Online Article Text |
id | pubmed-8321328 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-83213282021-08-26 Investigating the Potential of Network Optimization for a Constrained Object Detection Problem Ophoff, Tanguy Gullentops, Cédric Van Beeck, Kristof Goedemé, Toon J Imaging Article Object detection models are usually trained and evaluated on highly complicated, challenging academic datasets, which results in deep networks requiring lots of computations. However, a lot of operational use-cases consist of more constrained situations: they have a limited number of classes to be detected, less intra-class variance, less lighting and background variance, constrained or even fixed camera viewpoints, etc. In these cases, we hypothesize that smaller networks could be used without deteriorating the accuracy. However, there are multiple reasons why this does not happen in practice. Firstly, overparameterized networks tend to learn better, and secondly, transfer learning is usually used to reduce the necessary amount of training data. In this paper, we investigate how much we can reduce the computational complexity of a standard object detection network in such constrained object detection problems. As a case study, we focus on a well-known single-shot object detector, YoloV2, and combine three different techniques to reduce the computational complexity of the model without reducing its accuracy on our target dataset. To investigate the influence of the problem complexity, we compare two datasets: a prototypical academic (Pascal VOC) and a real-life operational (LWIR person detection) dataset. The three optimization steps we exploited are: swapping all the convolutions for depth-wise separable convolutions, perform pruning and use weight quantization. The results of our case study indeed substantiate our hypothesis that the more constrained a problem is, the more the network can be optimized. On the constrained operational dataset, combining these optimization techniques allowed us to reduce the computational complexity with a factor of 349, as compared to only a factor 9.8 on the academic dataset. When running a benchmark on an Nvidia Jetson AGX Xavier, our fastest model runs more than 15 times faster than the original YoloV2 model, whilst increasing the accuracy by 5% Average Precision (AP). MDPI 2021-04-01 /pmc/articles/PMC8321328/ /pubmed/34460514 http://dx.doi.org/10.3390/jimaging7040064 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Ophoff, Tanguy Gullentops, Cédric Van Beeck, Kristof Goedemé, Toon Investigating the Potential of Network Optimization for a Constrained Object Detection Problem |
title | Investigating the Potential of Network Optimization for a Constrained Object Detection Problem |
title_full | Investigating the Potential of Network Optimization for a Constrained Object Detection Problem |
title_fullStr | Investigating the Potential of Network Optimization for a Constrained Object Detection Problem |
title_full_unstemmed | Investigating the Potential of Network Optimization for a Constrained Object Detection Problem |
title_short | Investigating the Potential of Network Optimization for a Constrained Object Detection Problem |
title_sort | investigating the potential of network optimization for a constrained object detection problem |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8321328/ https://www.ncbi.nlm.nih.gov/pubmed/34460514 http://dx.doi.org/10.3390/jimaging7040064 |
work_keys_str_mv | AT ophofftanguy investigatingthepotentialofnetworkoptimizationforaconstrainedobjectdetectionproblem AT gullentopscedric investigatingthepotentialofnetworkoptimizationforaconstrainedobjectdetectionproblem AT vanbeeckkristof investigatingthepotentialofnetworkoptimizationforaconstrainedobjectdetectionproblem AT goedemetoon investigatingthepotentialofnetworkoptimizationforaconstrainedobjectdetectionproblem |