Vehicle classification using ResNets, localisation and spatially-weighted pooling

10/15/2018
by   Rohan Watkins, et al.
0

We investigate whether ResNet architectures can outperform more traditional Convolutional Neural Networks on the task of fine-grained vehicle classification. We train and test ResNet-18, ResNet-34 and ResNet-50 on the Comprehensive Cars dataset without pre-training on other datasets. We then modify the networks to use Spatially Weighted Pooling. Finally, we add a localisation step before the classification process, using a network based on ResNet-50. We find that using Spatially Weighted Pooling and localisation both improve classification accuracy of ResNet50. Spatially Weighted Pooling increases accuracy by 1.5 percent points and localisation increases accuracy by 3.4 percent points. Using both increases accuracy by 3.7 percent points giving a top-1 accuracy of 96.351% on the Comprehensive Cars dataset. Our method achieves higher accuracy than a range of methods including those that use traditional CNNs. However, our method does not perform quite as well as pre-trained networks that use Spatially Weighted Pooling.

READ FULL TEXT
research
04/07/2020

Pooling in Graph Convolutional Neural Networks

Graph convolutional neural networks (GCNNs) are a powerful extension of ...
research
11/17/2019

ELoPE: Fine-Grained Visual Classification with Efficient Localization, Pooling and Embedding

The task of fine-grained visual classification (FGVC) deals with classif...
research
06/08/2018

A Systematic Evaluation of Recent Deep Learning Architectures for Fine-Grained Vehicle Classification

Fine-grained vehicle classification is the task of classifying make, mod...
research
11/18/2019

Neural Forest Learning

We propose Neural Forest Learning (NFL), a novel deep learning based ran...
research
04/10/2020

Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?

How can we collect and use a video dataset to further improve spatiotemp...
research
08/02/2016

CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016

This paper presents the method that underlies our submission to the untr...
research
05/26/2023

Dual Bayesian ResNet: A Deep Learning Approach to Heart Murmur Detection

This study presents our team PathToMyHeart's contribution to the George ...

Please sign up or login with your details

Forgot password? Click here to reset