相关论文: Wavelet Convolutions for Large Receptive Fields

We study characteristics of receptive fields of units in deep convolutional networks. The receptive field size is a crucial issue in many visual tasks, as the output must respond to large enough areas in the image to capture information…

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with…

Vision Transformer (ViT) has demonstrated significant potential in various vision tasks due to its strong ability in modelling long-range dependencies. However, such success is largely fueled by training on massive samples. In real…

Convolutional networks have achieved great success in various vision tasks. This is mainly due to a considerable amount of research on network structure. In this study, instead of focusing on architectures, we focused on the convolution…

In standard Convolutional Neural Networks (CNNs), the receptive fields of artificial neurons in each layer are designed to share the same size. It is well-known in the neuroscience community that the receptive field size of visual cortical…

Transformers are popular neural network models that use layers of self-attention and fully-connected nodes with embedded tokens. Vision Transformers (ViT) adapt transformers for image recognition tasks. In order to do this, the images are…

Modeling long-range interactions, the propagation of information across distant parts of a graph, is a central challenge in graph machine learning. Graph wavelets, inspired by multi-resolution signal processing, provide a principled way to…

Spatial and spectral approaches are two major approaches for image processing tasks such as image classification and object recognition. Among many such algorithms, convolutional neural networks (CNNs) have recently achieved significant…

Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks. In this work, we show that while Transformers tend to have larger model capacity, their generalization…

We present a logarithmic-scale efficient convolutional neural network architecture for edge devices, named WaveletNet. Our model is based on the well-known depthwise convolution, and on two new layers, which we introduce in this work: a…

Learned image compression (LIC) has recently made significant progress, surpassing traditional methods. However, most LIC approaches operate mainly in the spatial domain and lack mechanisms for reducing frequency-domain correlations. To…

Deep image registration has demonstrated exceptional accuracy and fast inference. Recent advances have adopted either multiple cascades or pyramid architectures to estimate dense deformation fields in a coarse-to-fine manner. However, due…

The hybrid architecture of convolutional neural networks (CNNs) and Transformer are very popular for medical image segmentation. However, it suffers from two challenges. First, although a CNNs branch can capture the local image features…

Recent advancements in convolutional neural network (CNN)-based techniques for remote sensing pansharpening have markedly enhanced image quality. However, conventional convolutional modules in these methods have two critical drawbacks.…

The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks. However, the self-attention mechanism of…

Convolutional Neural Networks (CNNs) are known for requiring extensive computational resources, and quantization is among the best and most common methods for compressing them. While aggressive quantization (i.e., less than 4-bits) performs…

In the realm of deep learning, spatial attention mechanisms have emerged as a vital method for enhancing the performance of convolutional neural networks. However, these mechanisms possess inherent limitations that cannot be overlooked.…

Temporal/spatial receptive fields of models play an important role in sequential/spatial tasks. Large receptive fields facilitate long-term relations, while small receptive fields help to capture the local details. Existing methods…

This paper proposes Omnidirectional Representations from Transformers (OmniNet). In OmniNet, instead of maintaining a strictly horizontal receptive field, each token is allowed to attend to all tokens in the entire network. This process can…

Recent work in neural networks for image classification has seen a strong tendency towards increasing the spatial context. Whether achieved through large convolution kernels or self-attention, models scale poorly with the increased spatial…