2016/04/15 by Miao Sun, Sun, Miao, Tony Xiao Han +8 · 6 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Artificial intelligence #Artificial neural network #Benchmark (surveying) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Contextual image classification #Convolutional neural network #Deep learning #Discriminative model #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Feature (linguistics) #Image (mathematics) #MNIST database #Machine learning #Overfitting #Pascal (unit) #Pattern recognition (psychology) #Pooling #cs.CV
paper · pdf · doi:10.48550/arxiv.1604.04333
published in arXiv (Cornell University) (Cornell University) · International Conference on Pattern Recognition (ICPR) 2016
openalex publication_date 2016/04/15 · arxiv created 2016/10/11 · arxiv updated 2016/10/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deep Convolutional Neural Networks (CNN) have exhibited superior performance in many visual recognition tasks including image classification, object detection, and scene label- ing, due to their large learning capacity and resistance to overfit. For the image classification task, most of the current deep CNN- based approaches take the whole size-normalized image as input and have achieved quite promising results. Compared with the previously dominating approaches based on feature extraction, pooling, and classification, the deep CNN-based approaches mainly rely on the learning capability of deep CNN to achieve superior results: the burden of minimizing intra-class variation while maximizing inter-class difference is entirely dependent on the implicit feature learning component of deep CNN; we rely upon the implicitly learned filters and pooling component to select the discriminative regions, which correspond to the activated neurons. However, if the irrelevant regions constitute a large portion of the image of interest, the classification performance of the deep CNN, which takes the whole image as input, can be heavily affected. To solve this issue, we propose a novel latent CNN framework, which treats the most discriminate region as a latent variable. We can jointly learn the global CNN with the latent CNN to avoid the aforementioned big irrelevant region issue, and our experimental results show the evident advantage of the proposed latent CNN over traditional deep CNN: latent CNN outperforms the state-of-the-art performance of deep CNN on standard benchmark datasets including the CIFAR-10, CIFAR- 100, MNIST and PASCAL VOC 2007 Classification dataset.