相关论文: MixConv: Mixed Depthwise Convolutional Kernels

We propose a new convolution called Dynamic Region-Aware Convolution (DRConv), which can automatically assign multiple filters to corresponding spatial regions where features have similar representation. In this way, DRConv outperforms…

Deep Neural Networks, particularly Convolutional Neural Networks (ConvNets), have achieved incredible success in many vision tasks, but they usually require millions of parameters for good accuracy performance. With increasing applications…

We propose Re-parameterized Refocusing Convolution (RefConv) as a replacement for regular convolutional layers, which is a plug-and-play module to improve the performance without any inference costs. Specifically, given a pre-trained model,…

Deep learning methods have predominantly been applied to large artificial neural networks. Despite their state-of-the-art performance, these large networks typically do not generalize well to datasets with limited sample sizes. In this…

Dynamic convolution learns a linear mixture of $n$ static kernels weighted with their sample-dependent attentions, demonstrating superior performance compared to normal convolution. However, existing designs are parameter-inefficient: they…

Designing convolutional neural networks (CNN) for mobile devices is challenging because mobile models need to be small and fast, yet still accurate. Although significant efforts have been dedicated to design and improve mobile CNNs on all…

Object detection, one of the three main tasks of computer vision, has been used in various applications. The main process is to use deep neural networks to extract the features of an image and then use the features to identify the class and…

As deep learning (DL) is being rapidly pushed to edge computing, researchers invented various ways to make inference computation more efficient on mobile/IoT devices, such as network pruning, parameter compression, and etc. Quantization, as…

Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise…

Convolutional Neural Networks (CNNs) have achieved remarkable success in various computer vision tasks but rely on tremendous computational cost. To solve this problem, existing approaches either compress well-trained large-scale models or…

Mixed-precision neural network (MPNN) that utilizes just enough data width for the neural network processing is an effective approach to meet the stringent resources constraints including memory and computing of MCUs. Nevertheless, there is…

Convolution Neural Networks (CNNs) are widely used in medical image analysis, but their performance degrade when the magnification of testing images differ from the training images. The inability of CNNs to generalize across magnification…

Vision transformers (ViTs) have dominated computer vision in recent years. However, ViTs are computationally expensive and not well suited for mobile devices; this led to the prevalence of convolutional neural network (CNN) and ViT-based…

There has been exploding interest in embracing Transformer-based architectures for medical image segmentation. However, the lack of large-scale annotated medical datasets make achieving performances equivalent to those in natural images…

In low light or short-exposure photography the image is often corrupted by noise. While longer exposure helps reduce the noise, it can produce blurry results due to the object and camera motion. The reconstruction of a noise-less image is…

Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition. However, they face notable challenges in performance and computational efficiency when dealing with real-world, multi-scale…

The tradeoff between receptive field size and efficiency is a crucial issue in low level vision. Plain convolutional networks (CNNs) generally enlarge the receptive field at the expense of computational cost. Recently, dilated filtering has…

Object detection has made substantial progress in the last decade, due to the capability of convolution in extracting local context of objects. However, the scales of objects are diverse and current convolution can only process single-scale…

Depth estimation is a crucial step for 3D reconstruction with panorama images in recent years. Panorama images maintain the complete spatial information but introduce distortion with equirectangular projection. In this paper, we propose an…

Deep neural networks are increasingly used on mobile devices, where computational resources are limited. In this paper we develop CondenseNet, a novel network architecture with unprecedented efficiency. It combines dense connectivity with a…