Bird species classification has received more and more attention in the field
of computer vision, for its promising applications in biology and environmental
studies. Recognizing bird species is difficult due to the challenges of
discriminative region localization and fine-grained feature learning. In this
paper, we have introduced a Transfer learning based method with multistage
training. We have used both Pre-Trained Mask-RCNN and an ensemble model
consisting of Inception Nets (InceptionV3 & InceptionResNetV2 ) to get
localization and species of the bird from the images respectively. Our final
model achieves an F1 score of 0.5567 or 55.67 % on the dataset provided in CVIP
2018 Challenge.
Description
Bird Species Classification using Transfer Learning with Multistage Training
%0 Generic
%1 das2018species
%A Das, Sourya Dipta
%A Kumar, Akash
%D 2018
%K machinelearn
%T Bird Species Classification using Transfer Learning with Multistage
Training
%U http://arxiv.org/abs/1810.04250
%X Bird species classification has received more and more attention in the field
of computer vision, for its promising applications in biology and environmental
studies. Recognizing bird species is difficult due to the challenges of
discriminative region localization and fine-grained feature learning. In this
paper, we have introduced a Transfer learning based method with multistage
training. We have used both Pre-Trained Mask-RCNN and an ensemble model
consisting of Inception Nets (InceptionV3 & InceptionResNetV2 ) to get
localization and species of the bird from the images respectively. Our final
model achieves an F1 score of 0.5567 or 55.67 % on the dataset provided in CVIP
2018 Challenge.
@misc{das2018species,
abstract = {Bird species classification has received more and more attention in the field
of computer vision, for its promising applications in biology and environmental
studies. Recognizing bird species is difficult due to the challenges of
discriminative region localization and fine-grained feature learning. In this
paper, we have introduced a Transfer learning based method with multistage
training. We have used both Pre-Trained Mask-RCNN and an ensemble model
consisting of Inception Nets (InceptionV3 & InceptionResNetV2 ) to get
localization and species of the bird from the images respectively. Our final
model achieves an F1 score of 0.5567 or 55.67 % on the dataset provided in CVIP
2018 Challenge.},
added-at = {2019-07-14T16:03:36.000+0200},
author = {Das, Sourya Dipta and Kumar, Akash},
biburl = {https://www.bibsonomy.org/bibtex/2de8e4112b907dcb904851e21895363e6/cmcneile},
description = {Bird Species Classification using Transfer Learning with Multistage Training},
interhash = {4c4e2cf59e76373f3797974b6058558f},
intrahash = {de8e4112b907dcb904851e21895363e6},
keywords = {machinelearn},
note = {cite arxiv:1810.04250},
timestamp = {2019-07-14T16:03:36.000+0200},
title = {Bird Species Classification using Transfer Learning with Multistage
Training},
url = {http://arxiv.org/abs/1810.04250},
year = 2018
}