2018 25th IEEE International Conference on Image Processing (ICIP)

Deep convolutional neural networks have become the state of the art methods for image classification after demonstrating very good performance on very large datasets with general visual content. Amongst the problems for training deep CNN architectures is the heavy computational cost and the large memory requirements. In this work we exploit the fact that many training samples are correctly classif... View full abstract»

With the ever increasing application of Convolutional Neural Networks to customer products the need emerges for models to efficiently run on embedded, mobile hardware. Slimmer models have therefore become a hot research topic with various approaches which vary from binary networks to revised convolution layers. We offer our contribution to the latter and propose a novel convolution block which sig... View full abstract»

Pruning filters is an effective method for accelerating deep neural networks (DNNs), but most existing approaches prune filters on a pre-trained network directly which limits in acceleration. Although each filter has its own effect in DNNs, but if two filters are same with each other, we could prune one safely. In this paper, we add an extra cluster loss term in the loss function which can force f... View full abstract»

Finding visual features and suitable models for lipreading tasks that are more complex than a well-constrained vocabulary has proven challenging. This paper explores state-of-the-art Deep Neural Network architectures for lipreading based on a Sequence to Sequence Recurrent Neural Network. We report results for both hand-crafted and 2D/3D Convolutional Neural Network visual front-ends, online monot... View full abstract»

Noisy labels modeling makes a convolutional neural network (CNN) more robust for the image classification problem. However, current noisy labels modeling methods usually require an expectation-maximization (EM) based procedure to optimize the parameters, which is computationally expensive. In this paper, we utilize a fast annealing training method to speed up the CNN training in every M-step. Sinc... View full abstract»

Non-regular sampling can reduce aliasing at the expense of noise. Recently, it has been shown that non-regular sampling can be carried out using a conventional regular imaging sensor when the surface of its individual pixels is partially covered. This technique is called quarter sampling (also 1/4 sampling), since only one quarter of each pixel is sensitive to light. For this purpose, the choice o... View full abstract»

This paper addresses two main issues present in compressive imaging: namely, the issue of long acquisition time by using a single-pixel sensor and that of high computational complexity for high-resolution image recovery. We show that these issues are resolved in a new architecture, which is referred to as block-based compressive imaging. The new architecture consists of a lens, a programmable aper... View full abstract»

Recently emerging applications, such as autonomous navigation, mapping, and home entertainment, have increased the demand for inexpensive and high quality depth sensing. In this paper we fundamentally re-examine the problem, considering recent advances in photoelectric devices, increased availability of fast electronics, reduced computation cost, and developments in sensing theory. Our main contri... View full abstract»

Recently, light field image has attracted wide attention. However, much less work has been conducted on the perceptual evaluation of light field image. In this work, we create the first windowed 5 degree of freedom light field image database (Win5-LID) based on stereoscopic display, which provides windowed 5 DOF experience and all the depth cues of light field image. The database consists of light... View full abstract»

As a successful deep model applied in image compressed sensing, the Compressed Sensing Network (CSNet) has demonstrated superior performance to the previous handcrafted models in both running speed and reconstruction quality. However, CSNet trains different models for different sampling rates that hinders it from practical usage since too many models need to store. In this paper, we propose multi-... View full abstract»

Recent research on image super-resolution (SR) has shown that the use of perceptual losses such as feature-space loss functions and adversarial training can greatly improve the perceptual quality of the resulting SR output. In this paper, we extend the use of these perceptual-focused approaches for image SR to that of video SR. We design a 15-block residual neural network, VSRResNet, which is pre-... View full abstract»

We propose a method for super-resolution (SR) of low-resolution (LR) color images taken in low-light scenes. Our method is based on multi-frame SR technique, which fuses multiple LR images taken at different camera positions to synthesize a high-resolution color image. Previous methods have implicitly assumed that LR images could be captured with less noise and blur. However, heavy noise and motio... View full abstract»

Face hallucination technique generates high-resolution (HR) face images from low-resolution (LR) ones. In this paper, we propose to use a coarse-to-fine method for face hallucination by constructing a two-branch network, which makes full use of the specific prior knowledge of face images and the advantages of generic image super-resolution (SR) methods. Specifically, we jointly build a deep neural... View full abstract»

It is well-known that a number of excellent super-resolution (SR) methods using convolutional neural networks (CNNs) generate checkerboard artifacts. A condition to avoid the checkerboard artifacts is proposed in this paper. So far, checkerboard artifacts have been mainly studied for linear multirate systems, but the condition to avoid checkerboard artifacts can not be applied to CNNs due to the n... View full abstract»

This paper proposes a method, Dense ByNet, for single image super-resolution based on a convolutional neural network (CNN). The main innovation is a new architecture that combines several CNN design choices. Using a residual network as a basis, it introduces dense connections inside residual blocks, significantly reducing the number of parameters. Second, we apply dilation convolutions to increase... View full abstract»

Camera-equipped drones have recently revolutionized aerial cinematography, allowing easy acquisition of impressive footage. Although they are currently manually operated, autonomous functionalities based on machine learning and computer vision are becoming popular. However, the emerging area of autonomous UAV filming has to face several challenges, especially when visually tracking fast and unpred... View full abstract»

An autonomous navigation system relies on a number of sensors including radar, LIDAR and a visible light camera for its operation. We focus our attention on the visible light camera in this work. Object detection is the key first step to processing the video input from the camera. Specifically, we address the problem of assessing the performance of object detection algorithms in hazardous driving ... View full abstract»