Abstract
Effective utilization on texture-less 3D models for deep learning is significant to recognition on real photos. We eliminate the reliance on massive real training data by modifying convolutional neural network in 3 aspects: synthetic data rendering for training data generation in large quantities, multi-triplet cost function modification for multi-task learning and compact micro architecture design for producing tiny parametric model while overcoming over-fit problem in texture-less models. Network is initiated with multi-triplet cost function establishing sphere-like distribution of descriptors in each category which is helpful for recognition on regular photos according to pose, lighting condition, background and category information of rendered images. Fine-tuning with additional data further meets the aim of classification on special real photos based on initial model. We propose a 6.2 MB compact parametric model called ZigzagNet based on SqueezeNet to improve the performance for recognition by applying moving normalization inside micro architecture and adding channel wise convolutional bypass through macro architecture. Moving batch normalization is used to get a good performance on both convergence speed and recognition accuracy. Accuracy of our compact parametric model in experiment on ImageNet and PASCAL samples provided by PASCAL3D+ based on simple Nearest Neighbor classifier is close to the result of 240 MB AlexNet trained with real images. Model trained on texture-less models which consumes less time for rendering and collecting outperforms the result of training with more textured models from ShapeNet.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Normal 4.8 MB model is stored by 8-bits reversible quantization as 2.9 MB with float min and max ranges. Quantization isn’t included in the training process.
References
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. CoRR abs/1409.4842 (2014)
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R.B., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. CoRR abs/1408.5093 (2014)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation (2015)
Iandola, F.N., Moskewicz, M.W., Ashraf, K., Han, S., Dally, W.J., Keutzer, K.: SqueezeNet: Alexnet-level accuracy with 50\(\times \) fewer parameters and \(<{1}\) MB model size. CoRR abs/1602.07360 (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105. Curran Associates Inc. (2012)
Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, inception-resnet and the impact of residual connections on learning. CoRR abs/1602.07261 (2016)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision (2015)
Wohlhart, P., Lepetit, V.: Learning descriptors for object recognition and 3D pose estimation. In: Proceedings of the IEEE CVPR (2015)
Pepik, B., Benenson, R., Ritschel, T., Schiele, B.: What is holding back convnets for detection? CoRR abs/1508.02844 (2015)
Xiang, Y., Mottaghi, R., Savarese, S.: Beyond PASCAL: a benchmark for 3D object detection in the wild. In: IEEE WACV (2014)
Courbariaux, M., Bengio, Y.: Binarynet: training deep neural networks with weights and activations constrained to \(+1\) or \(-1\). Clinical Orthopaedics and Related Research (2016)
Courbariaux, M., Bengio, Y., David, J.P.: Binaryconnect: training deep neural networks with binary weights during propagations (2015)
Gysel, P., Motamedi, M., Ghiasi, S.: Hardware-oriented approximation of convolutional neural networks (2016)
Su, H., Qi, C.R., Li, Y., Guibas, L.J.: Render for CNN: viewpoint estimation in images using CNNs trained with rendered 3D model views. In: The IEEE ICCV (2015)
Vedantham, A.: Guides. Flickr. Overview. (2013)
Dean, T., Ruzon, M., Segal, M., Shlens, J., Vijayanarasimhan, S., Yagnik, J.: Fast, accurate detection of 100,000 object classes on a single machine. In: 2013 IEEE Conference on CVPR, pp. 1814–1821 (2013)
Hinterstoisser, S., Lepetit, V., Ilic, S., Holzer, S., Bradski, G., Konolige, K., Navab, N.: Model based training, detection and pose estimation of texture-less 3D objects in heavily cluttered scenes. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7724, pp. 548–562. Springer, Heidelberg (2013). doi:10.1007/978-3-642-37331-2_42
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M.S., Berg, A.C., Li, F.: Imagenet large scale visual recognition challenge. CoRR abs/1409.0575 (2014)
Hinterstoisser, S., Benhimane, S., Lepetit, V., Fua, P., Navab, N.: Simultaneous recognition and homography extraction of local patches with a simple linear classifier. In: Proceedings of the BMVC, pp. 10.1–10.10. BMVA Press (2008)
Wang, J., Song, Y., Leung, T., Rosenberg, C., Wang, J., Philbin, J., Chen, B., Wu, Y.: Learning fine-grained image similarity with deep ranking. CoRR abs/1404.4661 (2014)
Jolliffe, I.T.: Principal component analysis. Technometrics (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. CoRR abs/1502.01852 (2015)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. CoRR abs/1502.03167 (2015)
Chang, A.X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., Xiao, J., Yi, L., Yu, F.: ShapeNet: an information-rich 3D model repository. Technical report arXiv:1512.03012 [cs.GR], Stanford University – Princeton University – Toyota Technological Institute at Chicago (2015)
Acknowledgments
This work was partially sponsored by supported by the NSFC (National Natural Science Foundation of China) under Grant No. 61375031, No. 61573068, No. 61471048, and No. 61273217, the Fundamental Research Funds for the Central Universities under Grant No. 2014ZD03-01, This work was also supported by Beijing Nova Program, CCF-Tencent Open Research Fund, and the Program for New Century Excellent Talents in University.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Wang, Y., Cui, C., Zhou, X., Deng, W. (2017). ZigzagNet: Efficient Deep Learning for Real Object Recognition Based on 3D Models. In: Lai, SH., Lepetit, V., Nishino, K., Sato, Y. (eds) Computer Vision – ACCV 2016. ACCV 2016. Lecture Notes in Computer Science(), vol 10114. Springer, Cham. https://doi.org/10.1007/978-3-319-54190-7_28
Download citation
DOI: https://doi.org/10.1007/978-3-319-54190-7_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-54189-1
Online ISBN: 978-3-319-54190-7
eBook Packages: Computer ScienceComputer Science (R0)