Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Published in:
Position Control of Pneumatic Actuator Using Cascade Fuzzy Self-adaptive PID Read chapter Read first chapter

2020 | OriginalPaper | Chapter

SCAR-CNN: Secondary-Classification-After-Refinement Convolutional Neural Network for Fine-Grained Categorization

Authors : Bernard Jun Kai Cheah, Abduljalil Radman, Shahrel Azmin Suandi

Published in: InECCE2019

Publisher: Springer Singapore

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

The majority of existing approaches for fine-grained image recognition that work on attention-based learning, have their respective Top-K prediction accuracy better than Top-1 prediction. It is to say, there is a significant number of correct class falls in the range of Top-K predictions where K = 2, 3, 4, 5. This is the indirect indication for researchers not to neglect the need to explore the possibility of getting better prediction based on the discriminative feature of Top-K classes. This paper presents Secondary-Classification-After-Refinement Convolutional Neural Network (SCAR-CNN) which have an adaptive secondary classification model built on top of primary classification Top-K classes. Our focus is also on how to maximize the effect of removing unwanted classes in secondary classification, by performing image-enhancement on the input image of primary classification. Experiments show that these approaches achieve 86.9% of total accuracy as compared to the current state-of-the-art 86.5%.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now
previous chapter Classification of Agarwood Types (Malaccensis and Crassna) Between Oil and Smoke Using E-Nose with CBR Classifier
next chapter Forecasting Road Deaths in Malaysia Using Support Vector Machine
Literature
1.
Lin T-Y, Roy Chowdhury A, Maji S (2018) Bilinear convolutional neural networks for fine-grained visual recognition. IEEE Trans Pattern Anal Mach Intell 40(6):1309–1322CrossRef
2.
Bargal SA, Zunino A, Petsiuk V, Zhang J, Saenko K, Murino V, Sclaroff S (2018) Guided zoom: questioning network evidence for fine-grained classification. Computer Research Repository (CoRR) 1812:02626
3.
Cai D, Chen K, Qian Y, Kämäräinen J-K (2019) Convolutional low-resolution fine-grained classification. Pattern Recogn Lett 119:166–171CrossRef
4.
Huang S, Xu Z, Tao D, Zhang Y (2016) Part-stacked CNN for fine-grained visual categorization. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 1173–1182
5.
Lin D, Shen X, Lu C, Jia J (2015) Deep LAC: deep localization, alignment and classification for fine-grained recognition. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 1666–1674
6.
Zhang Y, Wei X-S, Wu J, Cai J, Lu J, Nguyen V-A, Do MN (2016) Weakly supervised fine-grained categorization with part-based image representation. IEEE Trans Image Process 25(4):1713–1725MathSciNetCrossRef
7.
Wang J, Fu J, Xu Y, Mei T (2016) Beyond object recognition: visual sentiment analysis with deep coupled adjective and noun neural networks. In: International joint conference on artificial intelligence (IJCAI-16), p 7
8.
Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Commun ACM 60(6):84–90CrossRef
9.
Fu J, Mei T, Yang K, Lu H, Rui Y (2015) Tagging personal photos with transfer deep learning. In: Proceedings of the 24th international conference on world wide web—WWW ’15, pp 344–354. ACM Press, New York, NY, USA
10.
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 770–778
11.
Lin T-Y, Maji S (2017) Improved bilinear pooling with CNNs. In: British machine vision conference (BMVC), vol 2017
12.
Kong S, Fowlkes C (2017) Low-rank bilinear pooling for fine-grained classification. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 7025–7034
13.
Wu L, Wang Y (2017) Where to focus: deep attention-based spatially recurrent bilinear networks for fine-grained visual recognition. Computer Research Repository (CoRR), vol abs/1709.0
14.
Yu C, Zhao X, Zheng Q, Zhang P, You X (2018) Hierarchical bilinear pooling for fine-grained visual recognition. In: European conference on computer vision (ECCV), pp 595–610
15.
Perronnin F, Larlus D (June 2015) Fisher vectors meet neural networks: a hybrid classification architecture. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 3743–3752
16.
Zhao B, Wu X, Feng J, Peng Q, Yan S (2017) Diversified visual attention networks for fine-grained object classification. IEEE Trans Multimedia 19(6):1245–1256CrossRef
17.
Anderson A, Shaffer K, Yankov A, Corley C, Hodas NO (2017) Beyond fine tuning: a modular approach to learning on small data. Computer Research Repository (CoRR), vol. abs/1611.0, no. Nathan Hodas
18.
Hu Q, Wang H, Li T, Shen C (2017) Deep CNNs with spatially weighted pooling for fine-grained car recognition. IEEE Trans Intell Transp Syst 18(11):3147–3156CrossRef
19.
Zhang N, Donahue J, Girshick R, Darrell T (2014) Part-based R-CNNs for fine-grained category detection. In: European conference on computer vision (ECCV), pp 834–849
20.
Wei X-S, Xie C-W, Wu J, Shen C (2018) Mask-CNN: localizing parts and selecting descriptors for fine-grained bird species categorization. Pattern Recogn 76:704–714CrossRef
21.
Krause J, Jin H, Yang J, Fei-Fei L (June 2015) Fine-grained recognition without part annotations. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 5546–5555
22.
Zheng H, Fu J, Mei T, Luo J (2017) Learning multi-attention convolutional neural network for fine-grained image recognition. In: 2017 IEEE international conference on computer vision (ICCV), pp 5219–5227
23.
Fu J, Zheng H, Mei T (2017 ) Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 4476–4484
24.
Zhang H, Xu T, Elhoseiny M, Huang X, Zhang S, Elgammal A, Metaxas D (2016) SPDA-CNN: unifying semantic part detection and abstraction for fine-grained recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 1143–1152
25.
Xiao T, Xu Y, Yang K, Zhang J, Peng Y, Zhang Z (June 2015) The application of two-level attention models in deep convolutional neural network for fine-grained image classification. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 842–850
26.
Zhang X, Xiong H, Zhou W, Lin W, Tian Q (2016) Picking deep filter responses for fine-grained image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 1134–1142
27.
Wang D, Shen Z, Shao J, Zhang W, Xue X, Zhang Z (December 2015) Multiple granularity descriptors for fine-grained categorization. In: 2015 IEEE international conference on computer vision (ICCV), pp 2399–2406
28.
Bao J, Chen D, Wen F, Li H, Hua G (2017) CVAE-GAN: fine-grained image generation through asymmetric training. In: International conference on computer vision (ICCV)
29.
Welinder P, Branson S, Mita T, Wah C, Schroff F (2010) Caltech-UCSD Birds 200, tech. rep, California Institute of Technology
30.
Sun M (2018) Multi-attention multi-class constraint for fine-grained image recognition. In: European conference on computer vision (ECCV), vol. abs/1806.0
31.
Zhang Y, Tian Y, Kong Y, Zhong B, Fu Y (2018) Residual dense network for image super-resolution. In: 2018 IEEE/CVF conference on computer vision and pattern recognition, pp 2472–2481
32.
Mittal A, Moorthy AK, Bovik AC (2012) No-reference image quality assessment in the spatial domain. IEEE Trans Image Process 21(12):4695–4708MathSciNetCrossRef
33.
Liu X, Xia T, Wang J, Yang Y, Zhou F, Lin Y (2016) Fully convolutional attention networks for fine-grained recognition. Computer Research Repository (CoRR), vol. abs/1603.0
34.
Branson S, Horn GV, Belongie SJ, Perona P (2014) Bird species categorization using pose normalized deep convolutional nets. British Machine Vision Conference (BMVC), vol. abs/1406.2
35.
Li Z, Yang Y, Liu X, Zhou F, Wen S, Xu W (2017) Dynamic computational time for visual attention. In: 2017 IEEE international conference on computer vision workshops (ICCVW), pp 1199–1209
Metadata
Title
SCAR-CNN: Secondary-Classification-After-Refinement Convolutional Neural Network for Fine-Grained Categorization
Authors
Bernard Jun Kai Cheah
Abduljalil Radman
Shahrel Azmin Suandi
Copyright Year
2020
Publisher
Springer Singapore
Book
InECCE2019

Print ISBN: 978-981-15-2316-8

Electronic ISBN: 978-981-15-2317-5

Copyright Year: 2020

DOI
https://doi.org/10.1007/978-981-15-2317-5_21