Related papers: SAEN-BGS: Energy-Efficient Spiking AutoEncoder Net…

Deep neural networks for image super-resolution (SR) have demonstrated superior performance. However, the large memory and computation consumption hinders their deployment on resource-constrained devices. Binary neural networks (BNNs),…

Graph representation learning is a fundamental research issue and benefits a wide range of applications on graph-structured data. Conventional artificial neural network-based methods such as graph neural networks (GNNs) and variational…

Cross-domain person re-identification (re-ID) is challenging due to the bias between training and testing domains. We observe that if backgrounds in the training and testing datasets are very different, it dramatically introduces…

Spiking Neural Networks (SNNs) are a promising approach to low-power applications on neuromorphic hardware due to their energy efficiency. However, training SNNs is challenging because of the non-differentiable spike generation function. To…

In this paper, we propose several novel deep learning methods for object saliency detection based on the powerful convolutional neural networks. In our approach, we use a gradient descent method to iteratively modify an input image based on…

Unsupervised video segmentation plays an important role in a wide variety of applications from object identification to compression. However, to date, fast motion, motion blur and occlusions pose significant challenges. To address these…

Image foreground extraction is a classical problem in image processing and vision, with a large range of applications. In this dissertation, we focus on the extraction of text and graphics in mixed-content images, and design novel…

Scene background initialization allows the recovery of a clear image without foreground objects from a video sequence, which is generally the first step in many computer vision and video processing applications. The process may be strongly…

We introduce BSD-GAN, a novel multi-branch and scale-disentangled training method which enables unconditional Generative Adversarial Networks (GANs) to learn image representations at multiple scales, benefiting a wide range of generation…

Spiking Neural Networks (SNNs) exhibit exceptional energy efficiency on neuromorphic hardware due to their sparse activation patterns. However, conventional training methods based on surrogate gradients and Backpropagation Through Time…

This work presents a novel spiking neural network (SNN) decoding method, combining SNNs with Hyperdimensional computing (HDC). The goal is to create a decoding method with high accuracy, high noise robustness, low latency and low energy…

With sufficient paired training samples, the supervised deep learning methods have attracted much attention in image denoising because of their superior performance. However, it is still very challenging to widely utilize the supervised…

Spiking neural networks (SNNs), which mimic biological neural system to convey information via discrete spikes, are well known as brain-inspired models with excellent computing efficiency. By utilizing the surrogate gradient estimation for…

Although it has been widely discussed in video surveillance, background subtraction is still an open problem in the context of complex scenarios, e.g., dynamic backgrounds, illumination variations, and indistinct foreground objects. To…

Spiking neural networks (SNNs) that mimic information transmission in the brain can energy-efficiently process spatio-temporal information through discrete and sparse spikes, thereby receiving considerable attention. To improve accuracy and…

Convolutional neural networks (CNNs) are now the de facto solution for computer vision problems thanks to their impressive results and ease of learning. These networks are composed of layers of connected units called artificial neurons,…

Machine learning with artificial neural networks (ANNs), provides solutions for the growing complexity of modern communication systems. This complexity, however, increases power consumption, making the systems energy-intensive. Spiking…

Computer vision researchers have extensively worked on fundamental infrared visual recognition for the past few decades. Among various approaches, deep learning has emerged as the most promising candidate. However, Infrared Small Object…

Spiking neural networks (SNNs) can be used in low-power and embedded systems (such as emerging neuromorphic chips) due to their event-based nature. Also, they have the advantage of low computation cost in contrast to conventional artificial…

Recent deep learning models have demonstrated strong capabilities for classifying text and non-text components in natural images. They extract a high-level feature computed globally from a whole image component (patch), where the cluttered…