Deep Collaborative Learning Approach Over Object Recognition

The object recognition using deep neural networks have been most used in real applications. We proposes a framework for recognizing objects in very low resolution images through the collaborative learning of two deep neural networks consists of Image enhancement network Object recognition network. The image improvement network tries to enhance extremely low resolution images into sharper and more informative images with the use of collaborative learning signals from the object recognition network. The object recognition network with trained weights for high resolution images actively participates in the learning of the image enhancement network. It also utilizes the output from the image enhancement network as augmented learning data to boost its recognition performance on very low resolution objects. We verified that the proposed method can improve the image reconstruction and classification performance.