Since the convolutional neural network (CNN) is believed to find right features for a given problem, the study of hand-crafted features is somewhat neglected these days. In this paper, we show that finding an appropriate feature for the given problem may be still important as they can enhance the performance of CNN-based algorithms. Specifically, we show that feeding an appropriate feature to t...

Convolutional Neural Networks (CNN) has been a very popular area in large scale data processing and many works have demonstrate that CNN is a very promising tool in many field, e.g., image classification and image retrieval. Theoretically, CNN features can become better and better with the increase of CNN layers. But on the other side more layers can dramatically increase the computational cost...

Recent advances in remote sensing have witnessed a great amount of very high resolution (VHR) images acquired at sub-metre spatial resolution. These VHR remotely sensed data has post enormous challenges in processing, analysing and classifying them effectively due to the high spatial complexity and heterogeneity. Although many computer-aid classification methods that based on machine learning a...

Semantic-level land-use scene classification is a challenging problem, in which deep learning methods, e.g., convolutional neural networks (CNNs), have shown remarkable capacity. However, a lack of sufficient labeled images has proved a hindrance to increasing the land-use scene classification accuracy of CNNs. Aiming at this problem, this paper proposes a CNN pre-training method under the guid...

In recent years, research on decoding brain activity based on functional magnetic resonance imaging (fMRI) has made remarkable achievements. However, constraint-free natural image reconstruction from brain activity remains a challenge, as specifying brain activity for all possible images is impractical. The existing research simplified the problem by using semantic prior information or just rec...

We previously proposed a method of removing reflection artifacts in photoacoustic images that uses deep learning. Our approach generally relies on using simulated photoacoustic channel data to train a convolutional neural network (CNN) that is capable of distinguishing sources from artifacts based on unique differences in their spatial impulse responses (manifested as depth-based differences in...

In this paper, we study the sensitivity of CNN outputs with respect to image transformations and noise in the area of fine-grained recognition. In particular, we answer the following questions (1) how sensitive are CNNs with respect to image transformations encountered during wild image capture?; (2) can we increase the robustness of CNNs with respect to image degradations? and (3) how can we p...

Deep convolutional neural networks (CNNs) have had a major impact in most areas of image understanding, including object category detection. In object detection, methods such as R-CNN have obtained excellent results by integrating CNNs with region proposal generation algorithms such as selective search. In this paper, we investigate the role of proposal generation in CNN-based detectors in orde...

This paper suggests a method of applying convolutional neural network (CNN) to realtime moving-vehicle image dataset, and experiments its performances. Compared to Support vector machine (SVM), the CNN led to a 13.59% increase in performance.

Machine learning techniques are widely used in the domain of Natural Language Processing (NLP) and Computer Vision (CV), In order to capture complex and non-linear features deeper machine learning architectures become more and more popular. A lot of the state of art performance have been reported by employing deep learning techniques. Convolutional Neural Network (CNN) is one variant of deep le...