ABSTRACT
Feature extraction is the most important part of the whole object recognition and target detection system. Convolutional Networks have evolved to the state-of-the-art technique for computer vision tasks owing to the predominant feature extraction capability. However, the working process of Convolutional Networks is invisible, which makes it difficult to optimize the model. To evaluate a Convolutional Network, we introduce a novel way to project the activities back to the input pixel space, revealing what input pattern originally caused a specific activation in the feature maps. Using this visualization technique, we take the feature extraction of sunflower seed image containing an impurity as an example, and attempt to change the architecture of traditional Convolutional Networks in order to extract better specific features for target images. After a series of improvements, we got a new Convolutional Network which is more conducive to the target images feature extraction and the number of parameters is less than before, which is conducive to the transplantation of the small system. Our model can be docking the state-of-the-art recognition networks according to different application scenarios, so as to structure a complete automatic recognition system.
- Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005). Google ScholarDigital Library
- Lowe, D.: Distinctive image features from scale-invariant keypoints. In: IJCV (2004). Google ScholarDigital Library
- Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014). Google ScholarDigital Library
- LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Handwritten digit recognition with a back-propagation network. In: NIPS (1990).Google Scholar
- Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012). Google ScholarDigital Library
- He, K., Gkioxari, G., Dollár, P., & Girshick, R.: Mask R-CNN. In: ICCV (2017).Google ScholarCross Ref
- Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: CVPR (2016).Google Scholar
- Song, H., Huizi, M., William, J.D.: Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. In: ICLR (2016).Google Scholar
- Zeiler, M., & Fergus, R. Visualizing and understanding convolutional networks. In D. J. Fleet, T. Pajdla, B. Schiele, and T. Tuytelaars, editors, ECCV, volume 8689 of Lecture Notes in Computer Science, pages 818--833. Springer, (2014).Google Scholar
- Hinton, G.E., Osindero, S., Teh, Y.: A fast learning algorithm for deep belief nets. Neural Computation 18, 1527--1554 (2006). Google ScholarDigital Library
- LeCun, Y., Bengio, Y., Hinton, G.E.: Deep learning. Nature volume 521, pages 436--444. In: Nature (2015).Google Scholar
- Zeiler, M., Krishnan, D., Taylor, G., Fergus, R.: Deconvolutional networks. In: CVPR (2010).Google Scholar
- Zeiler, M., Taylor, G., Fergus, R.: Adaptive deconvolutional networks for mid and high level feature learning. In: ICCV (2011). Google ScholarDigital Library
- TensorFlow Homepage, https://www.tensorflow.org/, last accessed 2018/3/23.Google Scholar
- Chinese community of TensorFlow, http://www.tensorfly.cn/, last accessed 2018/4/15.Google Scholar
- Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks. In: ICLR (2014).Google Scholar
- Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015).Google Scholar
Index Terms
- Deep Neural Networks Optimization Based On Deconvolutional Networks
Recommendations
Evaluation of Visualization Methods' Effect on Convolutional Neural Networks Research
ACAI '18: Proceedings of the 2018 International Conference on Algorithms, Computing and Artificial IntelligenceIn recent years, as an important research hotspot in the field of artificial intelligence and machine learning, the convolutional neural network has made substantial breakthroughs and has been widely used. In order to better explore and understand its ...
Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions
AbstractWe propose a new type of neural networks, Kronecker neural networks (KNNs), that form a general framework for neural networks with adaptive activation functions. KNNs employ the Kronecker product, which provides an efficient way of ...
Deep Networks with RBF Layers to Prevent Adversarial Examples
Artificial Intelligence and Soft ComputingAbstractWe propose a simple way to increase the robustness of deep neural network models to adversarial examples. The new architecture obtained by stacking deep neural network and RBF network is proposed. It is shown on experiments that such architecture ...
Comments