Deep Regression Counting: Customized Datasets and Inter-Architecture Transfer Learning
The problem of regression counting is revisited and analyzed by generating custom data and simplified Residual Network architectures. The results provide three key insights: A deeper understanding of the inherent challenges to this problem with regards to the data characteristics; the influence of architecture depth on the regression counting performance; and ideas for a transfer learning strategy between dissimilar architectures that allow training deeper networks with knowledge gained from shallower ones. In a striking example, a network with 30 convolution layers is successfully initialized with the weights from a trained architecture containing only 7 convolutions, whereas convergence was previously unattainable with random initialization. The two datasets consist of 20,000 images containing 3 and 5 classes of shapes to be counted, respectively. The network architectures are simplified Residual Networks with varying depths. The images are made to be inexpensive computationally to train, allowing for easy future comparisons with the baseline set by this work.
KeywordsRegression counting Residual Networks Transfer learning
The authors acknowledge the National Council of Scientific Research and Development (CNPq) for partial funding of this project.
- 1.Aich, S., Stavness, I.: Object counting with small datasets of large imagesGoogle Scholar
- 2.Chollet, F., et al.: Keras (2015). https://keras.io
- 3.He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
- 4.Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
- 6.Lempitsky, V., Zisserman, A.: Learning to count objects in images. In: Advances in Neural Information Processing Systems (2010)Google Scholar
- 8.Rodriguez, A.C., Wegner, J.D.: Counting the uncountable: deep semantic density estimation from space. arXiv preprint arXiv:1809.07091 (2018)
- 9.Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
- 10.Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)Google Scholar
- 11.Veit, A., Wilber, M.J., Belongie, S.: Residual networks behave like ensembles of relatively shallow networks. In: Advances in Neural Information Processing Systems, pp. 550–558 (2016)Google Scholar
- 12.Venkatalakshmi, B., Thilagavathi, K.: Automatic red blood cell counting using hough transform. In: 2013 IEEE Conference on Information & Communication Technologies (ICT), pp. 267–271. IEEE (2013)Google Scholar