Related papers: Rethinking Token-Mixing MLP for MLP-based Vision B…

Recently, visual Transformer (ViT) and its following works abandon the convolution and exploit the self-attention operation, attaining a comparable or even higher accuracy than CNNs. More recently, MLP-Mixer abandons both the convolution…

For the past ten years, CNN has reigned supreme in the world of computer vision, but recently, Transformer has been on the rise. However, the quadratic computational cost of self-attention has become a serious problem in practice…

Convolutional Neural Networks (CNNs) are the go-to model for computer vision. Recently, attention-based networks, such as the Vision Transformer, have also become popular. In this paper we show that while convolutions and attention are both…

Recently, the proposed deep MLP models have stirred up a lot of interest in the vision community. Historically, the availability of larger datasets combined with increased computing capacity leads to paradigm shifts. This review paper…

Token-mixing multi-layer perceptron (MLP) models have shown competitive performance in computer vision tasks with a simple architecture and relatively small computational cost. Their success in maintaining computation efficiency is mainly…

In the field of computer vision, recent works show that a pure MLP architecture mainly stacked by fully-connected layers can achieve competing performance with CNN and transformer. An input image of vision MLP is usually split into multiple…

Transformers have sprung up in the field of computer vision. In this work, we explore whether the core self-attention module in Transformer is the key to achieving excellent performance in image recognition. To this end, we build an…

Recently, MLP-based vision backbones emerge. MLP-based vision architectures with less inductive bias achieve competitive performance in image recognition compared with CNNs and vision Transformers. Among them, spatial-shift MLP (S$^2$-MLP),…

Recently, MLP-like vision models have achieved promising performances on mainstream visual recognition tasks. In contrast with vision transformers and CNNs, the success of MLP-like models shows that simple information fusion operations…

Dense prediction in medical volume provides enriched guidance for clinical analysis. CNN backbones have met bottleneck due to lack of long-range dependencies and global context modeling power. Recent works proposed to combine vision…

Convolutional Neural Networks (CNNs) have been regarded as the go-to models for visual recognition. More recently, convolution-free networks, based on multi-head self-attention (MSA) or multi-layer perceptrons (MLPs), become more and more…

Due to their weak inductive bias, Multi-Layer Perceptrons (MLPs) have subpar performance at low-compute levels compared to standard architectures such as convolution-based networks (CNN). Recent work, however, has shown that the performance…

We present SpiralMLP, a novel architecture that introduces a Spiral FC layer as a replacement for the conventional Token Mixing approach. Differing from several existing MLP-based models that primarily emphasize axes, our Spiral FC layer is…

The three existing dominant network families, i.e., CNNs, Transformers, and MLPs, differ from each other mainly in the ways of fusing spatial contextual information, leaving designing more effective token-mixing mechanisms at the core of…

Vision Transformers have achieved impressive performance in many vision tasks. While the token mixer or attention block has been studied in great detail, much less research has been devoted to the channel mixer or feature mixing block (FFN…

Despite their simpler information fusion designs compared with Vision Transformers and Convolutional Neural Networks, Vision MLP architectures have demonstrated strong performance and high data efficiency in recent research. However,…

While attention-based transformer networks achieve unparalleled success in nearly all language tasks, the large number of tokens (pixels) found in images coupled with the quadratic activation memory usage makes them prohibitive for problems…

Neural networks are highly effective tools for image reconstruction problems such as denoising and compressive sensing. To date, neural networks for image reconstruction are almost exclusively convolutional. The most popular architecture is…

In deep learning, Multi-Layer Perceptrons (MLPs) have once again garnered attention from researchers. This paper introduces MC-MLP, a general MLP-like backbone for computer vision that is composed of a series of fully-connected (FC) layers.…

Self-attention and transformers have been widely used in deep learning. Recent efforts have been devoted to incorporating transformer blocks into different neural architectures, including those with convolutions, leading to various visual…