相关论文: Skip-Convolutions for Efficient Video Processing

Temporal convolution has been widely used for video classification. However, it is performed on spatio-temporal contexts in a limited view, which often weakens its capacity of learning video representation. To alleviate this problem, we…

To deliver ultra-high resolution 360-degree video (such as 8K, 12K, or even higher) across the internet, viewport-dependent streaming becomes necessary to save bandwidth. During viewport switches, clients and servers will instantly exchange…

For medical image semantic segmentation (MISS), Vision Transformers have emerged as strong alternatives to convolutional neural networks thanks to their inherent ability to capture long-range correlations. However, existing research uses…

We propose a collection of three shift-based primitives for building efficient compact CNN-based networks. These three primitives (channel shift, address shift, shortcut shift) can reduce the inference time on GPU while maintains the…

Since the breakthrough performance of AlexNet in 2012, convolutional neural networks (convnets) have grown into extremely powerful vision models. Deep learning researchers have used convnets to perform vision tasks with accuracy that was…

We propose a method for high-performance semantic image segmentation (or semantic pixel labelling) based on very deep residual networks, which achieves the state-of-the-art performance. A few design factors are carefully considered to this…

When a Convolutional Neural Network is used for on-the-fly evaluation of continuously updating time-sequences, many redundant convolution operations are performed. We propose the method of Deep Shifting, which remembers previously…

The recent advancement of edge computing enables researchers to optimize various deep learning architectures to employ them in edge devices. In this study, we aim to optimize Xception architecture which is one of the most popular deep…

MIMO (multiple input, multiple output) approaches are a recent trend in neural network architectures for video restoration problems, where each network evaluation produces multiple output frames. The video is split into non-overlapping…

We propose a hardware efficient quantum residual neural network which implements residual connections through a deterministic mixture of the identity operation and variational unitaries, enabling fully differentiable training. In contrast…

Group convolutional neural networks (G-CNNs) have been shown to increase parameter efficiency and model accuracy by incorporating geometric inductive biases. In this work, we investigate the properties of representations learned by regular…

While scale-invariant modeling has substantially boosted the performance of visual recognition tasks, it remains largely under-explored in deep networks based image restoration. Naively applying those scale-invariant techniques (e.g.…

Extending the translation equivariance property of convolutional neural networks to larger symmetry groups has been shown to reduce sample complexity and enable more discriminative feature learning. Further, exploiting additional symmetries…

This paper addresses representational block named Hierarchical-Split Block, which can be taken as a plug-and-play block to upgrade existing convolutional neural networks, improves model performance significantly in a network.…

Automatically detecting violence from surveillance footage is a subset of activity recognition that deserves special attention because of its wide applicability in unmanned security monitoring systems, internet video filtration, etc. In…

In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods. However, it is often required to assemble a large number of CLs, each containing thousands of parameters, in…

Convolutional Neural Networks (CNNs) have proven to be extremely accurate for image recognition, even outperforming human recognition capability. When deployed on battery-powered mobile devices, efficient computer architectures are required…

Binary convolutional networks have lower computational load and lower memory foot-print compared to their full-precision counterparts. So, they are a feasible alternative for the deployment of computer vision applications on limited…

We address the problem of efficiently compressing video for conferencing-type applications. We build on recent approaches based on image animation, which can achieve good reconstruction quality at very low bitrate by representing face…

Dilated Convolutions have been shown to be highly useful for the task of image segmentation. By introducing gaps into convolutional filters, they enable the use of larger receptive fields without increasing the original kernel size. Even…