In this paper we introduce a novel method for segmentation that can benefit from general semantics of Convolutional Neural Network (CNN). Our segmentation proposes visually and semantically coherent image segments. We use binary encoding of CNN features to overcome the difficulty of the clustering on the highdimensional CNN feature space. These binary encoding can be embedded into the CNN as an...

Cellular Neural Networks (CNN) have traditionally been used to perform nonlinear operations on images such as edge detection, hole filling, etc. However, algorithms for image compression using CNN have scarcely been explored. This paper presents new templates and novel algorithms to perform basic operations used for image compression. They include wavelet subband decomposition, computation of p...

The objective of this paper is the effective transfer of the Convolutional Neural Network (CNN) feature in image search and classification. Systematically, we study three facts in CNN transfer. 1) We demonstrate the advantage of using images with a properly large size as input to CNN instead of the conventionally resized one. 2) We benchmark the performance of different CNN layers improved by a...

This paper applies a convolutional neural network (CNN) trained for automatic speech recognition (ASR) to the task of speaker identification (SID). In the CNN/i-vector front end, the sufficient statistics are collected based on the outputs of the CNN as opposed to the traditional universal background model (UBM). Evaluated on heavily degraded speech data, the CNN/i-vector front end provides per...

Automatic segmentation of medical images is an important task for many clinical applications. In practice, a wide range of anatomical structures are visualised using different imaging modalities. In this paper, we investigate whether a single convolutional neural network (CNN) can be trained to perform different segmentation tasks. A single CNN is trained to segment six tissues in MR brain imag...

The relationship between Cellular Nonlinear Networks (CNNs) and Partial Differential Equations (PDEs) is investigated. The equivalence between discrete-space CNN models and continuousspace PDE models is rigorously defined. The key role of space discretization is explained. The problem of the equivalence is split into two sub-problems: approximation and topological equivalence, that can be expli...

In flies, Centrosomin (Cnn) forms a phosphorylation-dependent scaffold that recruits proteins to the mitotic centrosome, but how Cnn assembles into a scaffold is unclear. We show that scaffold assembly requires conserved leucine zipper (LZ) and Cnn-motif 2 (CM2) domains that co-assemble into a 2:2 complex in vitro. We solve the crystal structure of the LZ:CM2 complex, revealing that both protei...

This paper proposes two novel frontends for robust language identification (LID) using a convolutional neural network (CNN) trained for automatic speech recognition (ASR). In the CNN/i-vector frontend, the CNN is used to obtain the posterior probabilities for i-vector training and extraction instead of a universal background model (UBM). The CNN/posterior frontend is somewhat similar to a phone...

In this paper, we propose an image classification method for improving the learning speed of convolutional neural networks (CNN). Although CNN is widely used in multiclass image classification datasets, the learning speed remains slow for large amounts of data. Therefore, we attempted to improve the learning speed by applying an extreme learning machine (ELM). We propose a learning method combi...

Multi-character recognition in arbitrary photographs on mobile platform is difficult, in terms of both accuracy and real-time performance. In this paper, we focus on the domain of hand-written multi-digit recognition. Convolutional neural network (CNN) is the state-of-the-art solution for object recognition, and presents a workload that is both compute and data intensive. To reduce the workload...