Dense Neural Patterns and Innovative CNN Architectures for Efficient Object Detection and Image Classification

Authors

  • Bheesetty Srinivasa Rao

Keywords:

CNN, RNN, SVM, Object detection.

Abstract

This paper presents a comprehensive study on image classification and object detection, showcasing significant advancements in these domains. For object detection, we proposed an innovative approach by integrating Dense Neural Patterns (DNPs) with traditional detection frameworks, derived from deep convolutional neural networks (CNNs). This method notably improved performance in the Regionlets detection framework, achieving superior results on the PASCAL VOC datasets. In the realm of image classification, we introduced several key innovations: the Latent CNN, designed to manage multi-label images by focusing on discriminative regions; Multiple Instance Learning Convolutional Neural Networks (MILCNN), which enhance deep learning capabilities with limited labeled data; and the Residual Networks of Residual Networks (RoR) architecture, aimed at improving optimization. Despite these advancements, we identified areas for further improvement, such as speeding up detection through CNN-based bounding box proposals, advancing unsupervised learning techniques, and using RNNs with LSTM units to generate more effective image regions for classification.
 

Downloads

Download data is not yet available.

References

Subhransu Maji, Alexander C. Berg, and Jitendra Malik. Classification using intersection kernel support vector machines isefficient.

Chaitanya Desai, Deva Ramanan, and Charless C. Fowlkes. Discriminative models for multi-class object l ayout. International Journal of Computer Vision, 95(1):1–12,2011.

Pablo And r´es Arbel´aez, Jordi Pont-Tuset, Jonathan T. Barron, Ferran Marqu´es, and Jitendra Malik. Multiscale combinatorial grouping. In CVPR, 2014.

Ming ming Cheng, Ziming Zhang, Wen yan Lin, and Philip Torr. Binarized normed gradients for objectness estimation at 300fps. In in IEEECVPR, 2014.

J. Deng, A. Berg, S. Satheesh, H. Su, A. Khosla, and L. Fei-Fei. Imagenet large scale visual recognition competition 2012(ilsvrc2012). 2012.

Will Y. Zou, Xiaoyu Wang, Miao Sun, and Yuanqing Lin. Generic object detection with dense neural patterns and regionlets. In BMVC,2014.

Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. Imagenet classification with deep convolutional neural networks. In Neural Information Processing Systems, NIPS2012.

G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. In CoRR,2012.

W. Li, M. Zeiler, S. Zhang, Y. LeCun, and R. Fergus. Regularization of neural networks using dropconnect. In ICML,2013.

Dumitru Erhan, Yoshua Bengio, Aaron Courville, Pierre-Antoine Manzagol, Pascal Vincent, and Samy Bengio. Why does unsupervised pre-training help deep learning? In JMLR, volume 11(Feb), page 625660,2010.

J. Schmidhuber. Multi-column deep neural networks for image classification. In CVPR,2012.

Ali Sharif Razavian, Hossein Azizpour, Josephine Sullivan, and Stefan Carlsson. Cnn features off-the-shelf: an astounding baseline for recognition. In CVPR workshop,2014.

M. Everingham, L. Van Gool, C. Williams, J. Winn, and A. Zisserman. The pascal visual object classes challenge, 2010.

M. Everingham, L. Van Gool, C. Williams, J. Winn, and A. Zisserman. The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index. html.

Fahad Shahbaz Khan, Rao Muhammad Anwer, Joost van de Weijer, Andrew D. Bagdanov, Mar´ıa Vanrell, and Antonio M. L´opez. Color attributes for object detection. In CVPR,2012.

Timo Ahonen, Student Member, Abdenour Hadid, Matti Pietikinen, and Se- nior Member. Face description with local binary patterns: Application to face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28:2037–2041,2006.

Xiaoyu Wang, Tony X. Han, and Shuicheng Yan. An hog-lbp human detector with partial occlusion handling. In ICCV,2009.

Oncel Tuzel, Fatih Porikli, and Peter Meer. Pedestrian detection via classi- fication on riemannian manifolds. IEEE Trans. Pattern Anal. Mach. Intell., 30(10):1713–1727,2008.

Y. Boureau, F. Bach, Y. LeCun, and J. Ponce. Learning mid-level features for recognition. In CVPR,2010.

M. A. Wong J. A. Hartigan. Algorithm as 136: A k-means clustering algorithm. Applied Statistics, 28(1):100–108, 1979.

Downloads

Published

06.08.2024

How to Cite

Bheesetty Srinivasa Rao. (2024). Dense Neural Patterns and Innovative CNN Architectures for Efficient Object Detection and Image Classification. International Journal of Intelligent Systems and Applications in Engineering, 12(23s), 474–480. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/6891

Issue

Section

Research Article