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 tokens (patches), while the existing MLP models directly aggregate them with fixed weights, neglecting the varying semantic information of tokens from different images. To dynamically aggregate tokens, we propose to represent each token as a wave function with two parts, amplitude and phase. Amplitude is the original feature and the phase term is a complex value changing according to the semantic contents of input images. Introducing the phase term can dynamically modulate the relationship between tokens and fixed weights in MLP. Based on the wave-like token representation, we establish a novel Wave-MLP architecture for vision tasks. Extensive experiments demonstrate that the proposed Wave-MLP is superior to the state-of-the-art MLP architectures on various vision tasks such as image classification, object detection and semantic segmentation. The source code is available at https://github.com/huawei-noah/CV-Backbones/tree/master/wavemlp_pytorch and https://gitee.com/mindspore/models/tree/master/research/cv/wave_mlp.
Noah’s Ark Lab, Huawei Technologies（华为技术有限公司诺亚方舟实验室）；University of Sydney（悉尼大学）；Peking University（北京大学）
Previous vision MLPs such as MLP-Mixer and ResMLP accept linearly flattened image patches as input, making them inflexible for different input sizes and hard to capture spatial information. Such approach withholds MLPs from getting comparable performance with their transformer-based counterparts and prevents them from becoming a general backbone for computer vision. This paper presents Hire-MLP, a simple yet competitive vision MLP architecture via \textbf{Hi}erarchical \textbf{re}arrangement, which contains two levels of rearrangements. Specifically, the inner-region rearrangement is proposed …
The Chinese University of Hong Kong（香港中文大学）；National University of Singapore（新加坡国立大学）；Imperial College London（帝国理工学院）；National University of Singapore (Suzhou) Research Institute（新加坡国立大学（苏州）研究院）
Surgical captioning plays an important role in surgical instruction prediction and report generation. However, the majority of captioning models still rely on the heavy computational object detector or feature extractor to extract regional features. In addition, the detection model requires additional bounding box annotation which is costly and needs skilled annotators. These lead to inference delay and limit the captioning model to deploy in real-time robotic surgery. For this purpose, we design an end-to-end detector and feature extractor-free captioning model by utilizing the patch-based sh…
University of Oregon（俄勒冈大学）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；Picsart AI Research (PAIR)（Picsart人工智能研究院）
MLP-based architectures, which consist of a sequence of consecutive multi-layer perceptron blocks, have recently been found to reach comparable results to convolutional and transformer-based methods. However, most adopt spatial MLPs which take fixed dimension inputs, therefore making it difficult to apply them to downstream tasks, such as object detection and semantic segmentation. Moreover, single-stage designs further limit performance in other computer vision tasks and fully connected layers bear heavy computation. To tackle these problems, we propose ConvMLP: a hierarchical Convolutional M…
ShanghaiTech University（上海科技大学）；Tencent（腾讯）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程研究中心）；Shanghai Engineering Research Center of Energy Efficient and Custom AI IC（上海高效节能与定制AI芯片工程研究中心）
An Axial Shifted MLP architecture (AS-MLP) is proposed in this paper. Different from MLP-Mixer, where the global spatial feature is encoded for information flow through matrix transposition and one token-mixing MLP, we pay more attention to the local features interaction. By axially shifting channels of the feature map, AS-MLP is able to obtain the information flow from different axial directions, which captures the local dependencies. Such an operation enables us to utilize a pure MLP architecture to achieve the same local receptive field as CNN-like architecture. We can also design the recep…
Convolutional neural networks (CNNs) have demonstrated rapid progress and a high level of success in object detection. However, recent evidence has highlighted their vulnerability to adversarial attacks. These attacks are calculated image perturbations or adversarial patches that result in object misclassification or detection suppression. Traditional camouflage methods are impractical when applied to disguise aircraft and other large mobile assets from autonomous detection in intelligence, surveillance and reconnaissance technologies and fifth generation missiles. In this paper we present a u…
Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心）；Tsinghua University（清华大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；MEGVII Technology（旷视科技）；Aberystwyth University（阿伯里斯特威斯大学）
Compared to convolutional layers, fully-connected (FC) layers are better at modeling the long-range dependencies but worse at capturing the local patterns, hence usually less favored for image recognition. In this paper, we propose a methodology, Locality Injection, to incorporate local priors into an FC layer via merging the trained parameters of a parallel conv kernel into the FC kernel. Locality Injection can be viewed as a novel Structural Re-parameterization method since it equivalently converts the structures via transforming the parameters. Based on that, we propose a multi-layer-percep…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Facebook（脸书）
Vision transformer has demonstrated promising performance on challenging computer vision tasks. However, directly training the vision transformers may yield unstable and sub-optimal results. Recent works propose to improve the performance of the vision transformers by modifying the transformer structures, e.g., incorporating convolution layers. In contrast, we investigate an orthogonal approach to stabilize the vision transformer training without modifying the networks. We observe the instability of the training can be attributed to the significant similarity across the extracted patch represe…
Image registration is an essential but challenging task in medical image computing, especially for echocardiography, where the anatomical structures are relatively noisy compared to other imaging modalities. Traditional (non-learning) registration approaches rely on the iterative optimization of a similarity metric which is usually costly in time complexity. In recent years, convolutional neural network (CNN) based image registration methods have shown good effectiveness. In the meantime, recent studies show that the attention-based model (e.g., Transformer) can bring superior performance in p…
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), adopting the straightforward spatial-shift operation, achieves better performance than the pioneering works including MLP-mixer and ResMLP. More recently, using smaller patches with a pyramid structure, Vision Permutator (ViP) and Global Filter Network (GFNet) achieve better performance than S$^2$-MLP. In this paper, we improve the S$^2$-MLP vision backbone…
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 applications. There has been much research on architectures without CNN and self-attention in this context. In particular, MLP-Mixer is a simple architecture designed using MLPs and hit an accuracy comparable to the Vision Transformer. However, the only inductive bias in this architecture is the embedding of tokens. This leaves open the possibility of incorporating a …
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））
Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the underlying neural network, as the current state-of-the-art visual pretext tasks for SSL do not enjoy the benefit, i.e., they are architecture-agnostic. In particular, we focus on Vision Transformers (ViTs), which have gained much attention recently as a better architectural choice, often outperforming convolutional networks for various visual tasks. The unique c…
In the past decade, we have witnessed rapid progress in the machine vision backbone. By introducing the inductive bias from the image processing, convolution neural network (CNN) has achieved excellent performance in numerous computer vision tasks and has been established as \emph{de facto} backbone. In recent years, inspired by the great success achieved by Transformer in NLP tasks, vision Transformer models emerge. Using much less inductive bias, they have achieved promising performance in computer vision tasks compared with their CNN counterparts. More recently, researchers investigate usin…
This paper presents a model architecture for encoding the representations of part-whole hierarchies in images in form of a graph. The idea is to divide the image into patches of different levels and then treat all of these patches as nodes for a fully connected graph. A dynamic feature extraction module is used to extract feature representations from these patches in each graph iteration. This enables us to learn a rich graph representation of the image that encompasses the inherent part-whole hierarchical information. Utilizing proper self-supervised training techniques, such a model can be t…
MC-MLP:Multiple Coordinate Frames in all-MLP Architecture for Vision
School of Computer and Communication Engineering, University of Science and Technology Beijing（北京科技大学计算机与通信工程学院）；School of Life Science, Beijing Institute of Technology（北京理工大学生命学院）
The University of Texas at Austin（得克萨斯大学奥斯汀分校）；Microsoft Azure AI（微软Azure人工智能）
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 attributed to avoiding the use of self-attention that is often computationally heavy, yet this is at the expense of not being able to mix tokens both globally and locally. In this paper, to exploit both global and local dependencies without self-attention, we present Mix-Shift-MLP (MS-MLP) which makes the size of the local receptive field used for mixing incr…
National University of Singapore（新加坡国立大学）；Nankai University（南开大学）；Sea AI Labs（Sea人工智能实验室）
In this paper, we present Vision Permutator, a conceptually simple and data efficient MLP-like architecture for visual recognition. By realizing the importance of the positional information carried by 2D feature representations, unlike recent MLP-like models that encode the spatial information along the flattened spatial dimensions, Vision Permutator separately encodes the feature representations along the height and width dimensions with linear projections. This allows Vision Permutator to capture long-range dependencies along one spatial direction and meanwhile preserve precise positional in…
Peking University（北京大学）；University of California, Berkeley（加州大学伯克利分校）
Quantization is wildly taken as a model compression technique, which obtains efficient models by converting floating-point weights and activations in the neural network into lower-bit integers. Quantization has been proven to work well on convolutional neural networks and transformer-based models. Despite the decency of these models, recent works have shown that MLP-based models are able to achieve comparable results on various tasks ranging from computer vision, NLP to 3D point cloud, while achieving higher throughput due to the parallelism and network simplicity. However, as we show in the p…
Recently, vision architectures based exclusively on multi-layer perceptrons (MLPs) have gained much attention in the computer vision community. MLP-like models achieve competitive performance on a single 2D image classification with less inductive bias without hand-crafted convolution layers. In this work, we explore the effectiveness of MLP-based architecture for the view-based 3D object recognition task. We present an MLP-based architecture termed as Round-Roll MLP (R$^2$-MLP). It extends the spatial-shift MLP backbone by considering the communications between patches from different views. R…
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shanghai AI Laboratory（上海人工智能实验室）
We study how to represent a video with implicit neural representations (INRs). Classical INRs methods generally utilize MLPs to map input coordinates to output pixels. While some recent works have tried to directly reconstruct the whole image with CNNs. However, we argue that both the above pixel-wise and image-wise strategies are not favorable to video data. Instead, we propose a patch-wise solution, PS-NeRV, which represents videos as a function of patches and the corresponding patch coordinate. It naturally inherits the advantages of image-wise methods, and achieves excellent reconstruction…
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 attention-free network called sMLPNet based on the existing MLP-based vision models. Specifically, we replace the MLP module in the token-mixing step with a novel sparse MLP (sMLP) module. For 2D image tokens, sMLP applies 1D MLP along the axial directions and the parameters are shared among rows or columns. By sparse connection and weight sharing, sMLP module sign…
Tsinghua University（清华大学）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）
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 provides detailed discussions on whether MLP can be a new paradigm for computer vision. We compare the intrinsic connections and differences between convolution, self-attention mechanism, and Token-mixing MLP in detail. Advantages and limitations of Token-mixing MLP are provided, followed by careful analysis of recent MLP-like variants, from module design to netw…
NAVER AI Lab（NAVER人工智能实验室）；Seoul National University（首尔国立大学）
Recent studies have shown remarkable progress in GANs based on implicit neural representation (INR) - an MLP that produces an RGB value given its (x, y) coordinate. They represent an image as a continuous version of the underlying 2D signal instead of a 2D array of pixels, which opens new horizons for GAN applications (e.g., zero-shot super-resolution, image outpainting). However, training existing approaches require a heavy computational cost proportional to the image resolution, since they compute an MLP operation for every (x, y) coordinate. To alleviate this issue, we propose a multi-stage…
This paper studies the problem of designing compact binary architectures for vision multi-layer perceptrons (MLPs). We provide extensive analysis on the difficulty of binarizing vision MLPs and find that previous binarization methods perform poorly due to limited capacity of binary MLPs. In contrast with the traditional CNNs that utilizing convolutional operations with large kernel size, fully-connected (FC) layers in MLPs can be treated as convolutional layers with kernel size $1\times1$. Thus, the representation ability of the FC layers will be limited when being binarized, and places restri…
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 sufficient for good performance, neither of them are necessary. We present MLP-Mixer, an architecture based exclusively on multi-layer perceptrons (MLPs). MLP-Mixer contains two types of layers: one with MLPs applied independently to image patches (i.e. "mixing" the per-location features), and one with MLPs applied across patches (i.e. "mixing" spatial info…
Tencent（腾讯）；Tsinghua University（清华大学）；Peking University（北京大学）；Tencent AI Lab（腾讯人工智能实验室）
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 among tokens and channels can yield a good representation power for deep recognition models. However, existing MLP-like models fuse tokens through static fusion operations, lacking adaptability to the contents of the tokens to be mixed. Thus, customary information fusion procedures are not effective enough. To this end, this paper presents an efficient MLP-like …
Recently, vision transformers and MLP-based models have been developed in order to address some of the prevalent weaknesses in convolutional neural networks. Due to the novelty of transformers being used in this domain along with the self-attention mechanism, it remains unclear to what degree these architectures are robust to corruptions. Despite some works proposing that data augmentation remains essential for a model to be robust against corruptions, we propose to explore the impact that the architecture has on corruption robustness. We find that vision transformer architectures are inherent…
Vision-Transformers are widely used in various vision tasks. Meanwhile, there is another line of works starting with the MLP-mixer trying to achieve similar performance using mlp-based architectures. Interestingly, until now those mlp-based architectures have not been adapted for NLP tasks. Additionally, until now, mlp-based architectures have failed to achieve state-of-the-art performance in vision tasks. In this paper, we analyze the expressive power of mlp-based architectures in modeling dependencies between multiple different inputs simultaneously, and show an exponential gap between the a…
Arizona State University（亚利桑那州立大学）；Georgia State University（佐治亚州立大学）
Vision transformers require a huge amount of labeled data to outperform convolutional neural networks. However, labeling a huge dataset is a very expensive process. Self-supervised learning techniques alleviate this problem by learning features similar to supervised learning in an unsupervised way. In this paper, we propose a self-supervised technique PatchRot that is crafted for vision transformers. PatchRot rotates images and image patches and trains the network to predict the rotation angles. The network learns to extract both global and local features from an image. Our extensive experimen…
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 and the self-attention operation, proposing an architecture containing only MLP layers. To achieve cross-patch communications, it devises an additional token-mixing MLP besides the channel-mixing MLP. It achieves promising results when training on an extremely large-scale dataset. But it cannot achieve as outstanding performance as its CNN and ViT counterparts…
We initiate the first empirical study on the use of MLP architectures for vision-and-language (VL) fusion. Through extensive experiments on 5 VL tasks and 5 robust VQA benchmarks, we find that: (i) Without pre-training, using MLPs for multimodal fusion has a noticeable performance gap compared to transformers; (ii) However, VL pre-training can help close the performance gap; (iii) Instead of heavy multi-head attention, adding tiny one-head attention to MLPs is sufficient to achieve comparable performance to transformers. Moreover, we also find that the performance gap between MLPs and transfor…
Guangxi Normal University（广西师范大学）；Huaqiao University（华侨大学）；JD Explore Academy（京东探索研究院）
Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions. Despite having good success, the literature seldom explores the explainability of vision transformer, and there is no clear picture of how the attention mechanism with respect to the correlation across comprehensive patches will impact the performance and what is the further potential. In this work, we propose a novel explainable visualization approach to analyze and interpre…
We introduce the notion of a Patch Sampling Schedule (PSS), that varies the number of Vision Transformer (ViT) patches used per batch during training. Since all patches are not equally important for most vision objectives (e.g., classification), we argue that less important patches can be used in fewer training iterations, leading to shorter training time with minimal impact on performance. Additionally, we observe that training with a PSS makes a ViT more robust to a wider patch sampling range during inference. This allows for a fine-grained, dynamic trade-off between throughput and accuracy …
Tencent AI Lab（腾讯人工智能实验室）；Peking Union Medical College Hospital（北京协和医院）
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 transformer with CNN, due to its strong global capture ability and learning capability. However, most works are limited to simply applying pure transformer with several fatal flaws (i.e., lack of inductive bias, heavy computation and little consideration for 3D data). Therefore, designing an elegant and efficient vision transformer learner for dense prediction in m…
University of Science and Technology of China（中国科学技术大学）；Institute of Microelectronics, Chinese Academy of Sciences（中国科学院微电子研究所）；Singapore Management University（新加坡管理大学）；University of Manchester（曼彻斯特大学）
Vision multi-layer perceptrons (MLPs) have shown promising performance in computer vision tasks, and become the main competitor of CNNs and vision Transformers. They use token-mixing layers to capture cross-token interactions, as opposed to the multi-head self-attention mechanism used by Transformers. However, the heavily parameterized token-mixing layers naturally lack mechanisms to capture local information and multi-granular non-local relations, thus their discriminative power is restrained. To tackle this issue, we propose a new positional spacial gating unit (PoSGU). It exploits the atten…
Mixture-of-Experts (MoE), a conditional computation architecture, achieved promising performance by scaling local module (i.e. feed-forward network) of transformer. However, scaling the cross-token module (i.e. self-attention) is challenging due to the unstable training. This work proposes Sparse-MLP, an all-MLP model which applies sparsely-activated MLPs to cross-token modeling. Specifically, in each Sparse block of our all-MLP model, we apply two stages of MoE layers: one with MLP experts mixing information within channels along image patch dimension, the other with MLP experts mixing inform…
The Chinese University of Hong Kong（香港中文大学）；SmartMore
We study the vision transformer structure in the mobile level in this paper, and find a dramatic performance drop. We analyze the reason behind this phenomenon, and propose a novel irregular patch embedding module and adaptive patch fusion module to improve the performance. We conjecture that the vision transformer blocks (which consist of multi-head attention and feed-forward network) are more suitable to handle high-level information than low-level features. The irregular patch embedding module extracts patches that contain rich high-level information with different receptive fields. The tra…
Convolutional neural networks (CNN) are the dominant deep neural network (DNN) architecture for computer vision. Recently, Transformer and multi-layer perceptron (MLP)-based models, such as Vision Transformer and MLP-Mixer, started to lead new trends as they showed promising results in the ImageNet classification task. In this paper, we conduct empirical studies on these DNN structures and try to understand their respective pros and cons. To ensure a fair comparison, we first develop a unified framework called SPACH which adopts separate modules for spatial and channel processing. Our experime…
Technical University of Munich（慕尼黑工业大学）；Rice University（莱斯大学）
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 the U-Net, a convolutional network with a multi-resolution architecture. In this work, we show that a simple network based on the multi-layer perceptron (MLP)-mixer enables state-of-the art image reconstruction performance without convolutions and without a multi-resolution architecture, provided that the training set and the size of the network are moderat…
