This paper proposes the paradigm of large convolutional kernels in designing modern Convolutional Neural Networks (ConvNets). We establish that employing a few large kernels, instead of stacking multiple smaller ones, can be a superior design strategy. Our work introduces a set of architecture design guidelines for large-kernel ConvNets that optimize their efficiency and performance. We propose the UniRepLKNet architecture, which offers systematical architecture design principles specifically crafted for large-kernel ConvNets, emphasizing their unique ability to capture extensive spatial information without deep layer stacking. This results in a model that not only surpasses its predecessors with an ImageNet accuracy of 88.0%, an ADE20K mIoU of 55.6%, and a COCO box AP of 56.4% but also demonstrates impressive scalability and performance on various modalities such as time-series forecasting, audio, point cloud, and video recognition. These results indicate the universal modeling abilities of large-kernel ConvNets with faster inference speed compared with vision transformers. Our findings reveal that large-kernel ConvNets possess larger effective receptive fields and a higher shape bias, moving away from the texture bias typical of smaller-kernel CNNs. All codes and models are publicly available at https://github.com/AILab-CVC/UniRepLKNet promoting further research and development in the community.
Hong Kong University of Science and Technology（香港科技大学）
3D point cloud interpretation is a challenging task due to the randomness and sparsity of the component points. Many of the recently proposed methods like PointNet and PointCNN have been focusing on learning shape descriptions from point coordinates as point-wise input features, which usually involves complicated network architectures. In this work, we draw attention back to the standard 3D convolutions towards an efficient 3D point cloud interpretation. Instead of converting the entire point cloud into voxel representations like the other volumetric methods, we voxelize the sub-portions of th…
Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Shanghai Jiao Tong University（上海交通大学）；Meituan（美团）
The recent 3D medical ViTs (e.g., SwinUNETR) achieve the state-of-the-art performances on several 3D volumetric data benchmarks, including 3D medical image segmentation. Hierarchical transformers (e.g., Swin Transformers) reintroduced several ConvNet priors and further enhanced the practical viability of adapting volumetric segmentation in 3D medical datasets. The effectiveness of hybrid approaches is largely credited to the large receptive field for non-local self-attention and the large number of model parameters. In this work, we propose a lightweight volumetric ConvNet, termed 3D UX-Net, w…
Tsinghua University（清华大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
We propose a dynamic filtering strategy with large sampling field for ConvNets (LS-DFN), where the position-specific kernels learn from not only the identical position but also multiple sampled neighbor regions. During sampling, residual learning is introduced to ease training and an attention mechanism is applied to fuse features from different samples. Such multiple samples enlarge the kernels' receptive fields significantly without requiring more parameters. While LS-DFN inherits the advantages of DFN, namely avoiding feature map blurring by position-wise kernels while keeping translation i…
PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Meituan（美团）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Eindhoven University of Technology（埃因霍温理工大学）；University of Jyväskylä（于韦斯屈莱大学）；University of Twente（特文特大学）；University of Luxembourg（卢森堡大学）
Transformers have quickly shined in the computer vision world since the emergence of Vision Transformers (ViTs). The dominant role of convolutional neural networks (CNNs) seems to be challenged by increasingly effective transformer-based models. Very recently, a couple of advanced convolutional models strike back with large kernels motivated by the local-window attention mechanism, showing appealing performance and efficiency. While one of them, i.e. RepLKNet, impressively manages to scale the kernel size to 31x31 with improved performance, the performance starts to saturate as the kernel size…
Understanding the internal process of ConvNets is commonly done using visualization techniques. However, these techniques do not usually provide a tool for estimating the stability of a ConvNet against noise. In this paper, we show how to analyze a ConvNet in the frequency domain using a 4-dimensional visualization technique. Using the frequency domain analysis, we show the reason that a ConvNet might be sensitive to a very low magnitude additive noise. Our experiments on a few ConvNets trained on different datasets revealed that convolution kernels of a trained ConvNet usually pass most of th…
Center for Data Science, New York University（纽约大学数据科学中心）；Courant Institute of Mathematical Sciences, New York University（纽约大学库朗数学科学研究所）；Department of EECS, UC Berkeley（加州大学伯克利分校电气工程与计算机科学系）；Electrical and Computer Engineering, University of Denver（丹佛大学电气与计算机工程系）；Department of EECS, University of Michigan（密歇根大学电气工程与计算机科学系）
Normalization techniques have become a basic component in modern convolutional neural networks (ConvNets). In particular, many recent works demonstrate that promoting the orthogonality of the weights helps train deep models and improve robustness. For ConvNets, most existing methods are based on penalizing or normalizing weight matrices derived from concatenating or flattening the convolutional kernels. These methods often destroy or ignore the benign convolutional structure of the kernels; therefore, they are often expensive or impractical for deep ConvNets. In contrast, we introduce a simple…
MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation
German Cancer Research Center (DKFZ)（德国癌症研究中心）；Heidelberg University（海德堡大学）；National Center for Tumor Diseases (NCT)（国家肿瘤疾病中心）；University Medical Center Heidelberg（海德堡大学医院）；Helmholtz Imaging（亥姆霍兹成像机构）
ESAT-PSI, KU Leuven（鲁汶大学 ESAT-PSI）；Sensifai；University of Bonn（波恩大学）；CV:HCI, KIT, Karlsruhe（卡尔斯鲁厄理工学院 CV:HCI）
The work in this paper is driven by the question how to exploit the temporal cues available in videos for their accurate classification, and for human action recognition in particular? Thus far, the vision community has focused on spatio-temporal approaches with fixed temporal convolution kernel depths. We introduce a new temporal layer that models variable temporal convolution kernel depths. We embed this new temporal layer in our proposed 3D CNN. We extend the DenseNet architecture - which normally is 2D - with 3D filters and pooling kernels. We name our proposed video convolutional network …
This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features. By comparing the design principles of the recent convolutional neural networks ConvNets) and Vision Transformers, we propose to simplify the self-attention by leveraging a convolutional modulation operation. We show that such a simple approach can better take advantage of the large kernels (>=7x7) nested in convolutional layers. We build a family of hierarchical ConvNets using the proposed convolutional modulation, …
Carnegie Mellon University（卡内基梅隆大学）；Microsoft（微软）；Harbin Institute of Technology（哈尔滨工业大学）
Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the latency constraint of a mobile device? Neural Architecture Search (NAS) for ConvNet design is a challenging problem due to the combinatorially large design space and search time (at least 200 GPU-hours). To alleviate this complexity, we propose Single-Path NAS, a novel differentiable NAS method for designing device-efficient ConvNets in less than 4 hours. 1. Novel NAS formulation: our method introduces a single-path, over-parameterized ConvNet to encode all architectural decis…
We revisit the idea of brain damage, i.e. the pruning of the coefficients of a neural network, and suggest how brain damage can be modified and used to speedup convolutional layers. The approach uses the fact that many efficient implementations reduce generalized convolutions to matrix multiplications. The suggested brain damage process prunes the convolutional kernel tensor in a group-wise fashion by adding group-sparsity regularization to the standard training process. After such group-wise pruning, convolutions can be reduced to multiplications of thinned dense matrices, which leads to spee…
Institute of Neuroinformatics, University of Zürich and ETH Zürich（苏黎世大学与苏黎世联邦理工学院神经信息学研究所）
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 that use ConvNets, updating hundreds of networks for multiple tasks on an embedded device can be costly in terms of memory, bandwidth, and energy. Approaches to reduce this cost include model compression and parameter-efficient models that adapt a subset of network layers for each new task. This work proposes a novel parameter-efficient kernel modulation (KM…
Carnegie Mellon University（卡内基梅隆大学）；Microsoft（微软）；Harbin Institute of Technology（哈尔滨工业大学）
Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the runtime constraint of a mobile device? Neural architecture search (NAS) has revolutionized the design of hardware-efficient ConvNets by automating this process. However, the NAS problem remains challenging due to the combinatorially large design space, causing a significant searching time (at least 200 GPU-hours). To alleviate this complexity, we propose Single-Path NAS, a novel differentiable NAS method for designing hardware-efficient ConvNets in less than 4 hours. Our contr…
Facebook AI Research（脸书人工智能研究院）；Dartmouth College（达特茅斯学院）
We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are more suitable for spatiotemporal feature learning compared to 2D ConvNets; 2) A homogeneous architecture with small 3x3x3 convolution kernels in all layers is among the best performing architectures for 3D ConvNets; and 3) Our learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different …
In many robotics and VR/AR applications, 3D-videos are readily-available sources of input (a continuous sequence of depth images, or LIDAR scans). However, those 3D-videos are processed frame-by-frame either through 2D convnets or 3D perception algorithms. In this work, we propose 4-dimensional convolutional neural networks for spatio-temporal perception that can directly process such 3D-videos using high-dimensional convolutions. For this, we adopt sparse tensors and propose the generalized sparse convolution that encompasses all discrete convolutions. To implement the generalized sparse conv…
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）；MEGVII Technology（旷视科技）；Aberystwyth University（阿伯里斯特威斯大学）
We propose a universal building block of Convolutional Neural Network (ConvNet) to improve the performance without any inference-time costs. The block is named Diverse Branch Block (DBB), which enhances the representational capacity of a single convolution by combining diverse branches of different scales and complexities to enrich the feature space, including sequences of convolutions, multi-scale convolutions, and average pooling. After training, a DBB can be equivalently converted into a single conv layer for deployment. Unlike the advancements of novel ConvNet architectures, DBB complicate…
Johns Hopkins University（约翰斯·霍普金斯大学）；Canon Medical Research USA, INC.（佳能医疗研究美国公司）
A convolutional neural network (ConvNet) is usually trained and then tested using images drawn from the same distribution. To generalize a ConvNet to various tasks often requires a complete training dataset that consists of images drawn from different tasks. In most scenarios, it is nearly impossible to collect every possible representative dataset as a priori. The new data may only become available after the ConvNet is deployed in clinical practice. ConvNet, however, may generate artifacts on out-of-distribution testing samples. In this study, we present Targeted Gradient Descent (TGD), a nov…
Depthwise convolution is becoming increasingly popular in modern efficient ConvNets, but its kernel size is often overlooked. In this paper, we systematically study the impact of different kernel sizes, and observe that combining the benefits of multiple kernel sizes can lead to better accuracy and efficiency. Based on this observation, we propose a new mixed depthwise convolution (MixConv), which naturally mixes up multiple kernel sizes in a single convolution. As a simple drop-in replacement of vanilla depthwise convolution, our MixConv improves the accuracy and efficiency for existing Mobil…
University of Oxford（牛津大学）；DeepMind（DeepMind（谷歌旗下人工智能研究实验室））；Department of Engineering Science, University of Oxford（牛津大学工程科学系（注意：按要求提取到大学级别即可，此处仅作为补充说明，主要机构为牛津大学））；Google（谷歌（注意：原文本中作者邮箱显示为google.com，但未明确说明为谷歌机构，按要求仅提取明确出现的作者单位，此处DeepMind和牛津大学为明确机构））
The paucity of videos in current action classification datasets (UCF-101 and HMDB-51) has made it difficult to identify good video architectures, as most methods obtain similar performance on existing small-scale benchmarks. This paper re-evaluates state-of-the-art architectures in light of the new Kinetics Human Action Video dataset. Kinetics has two orders of magnitude more data, with 400 human action classes and over 400 clips per class, and is collected from realistic, challenging YouTube videos. We provide an analysis on how current architectures fare on the task of action classification …
Historically, the pursuit of efficient inference has been one of the driving forces behind research into new deep learning architectures and building blocks. Some recent examples include: the squeeze-and-excitation module, depthwise separable convolutions in Xception, and the inverted bottleneck in MobileNet v2. Notably, in all of these cases, the resulting building blocks enabled not only higher efficiency, but also higher accuracy, and found wide adoption in the field. In this work, we further expand the arsenal of efficient building blocks for neural network architectures; but instead of co…
Deep convolutional neural networks (ConvNets) of 3-dimensional kernels allow joint modeling of spatiotemporal features. These networks have improved performance of video and volumetric image analysis, but have been limited in size due to the low memory ceiling of GPU hardware. Existing CPU implementations overcome this constraint but are impractically slow. Here we extend and optimize the faster Winograd-class of convolutional algorithms to the $N$-dimensional case and specifically for CPU hardware. First, we remove the need to manually hand-craft algorithms by exploiting the relaxed constrain…
Single Image Inpainting and Super-Resolution with Simultaneous Uncertainty Guarantees by Universal Reproducing Kernels
Institute for Computer Science and Control (SZTAKI)（计算机科学与控制研究所）；Institute of Mathematics, Budapest University of Technology and Economics (BME)（布达佩斯技术大学数学研究所）
Massachusetts Institute of Technology（麻省理工学院）；Princeton University（普林斯顿大学）
Convolutional networks (ConvNets) have become a popular approach to computer vision. It is important to accelerate ConvNet training, which is computationally costly. We propose a novel parallel algorithm based on decomposition into a set of tasks, most of which are convolutions or FFTs. Applying Brent's theorem to the task dependency graph implies that linear speedup with the number of processors is attainable within the PRAM model of parallel computation, for wide network architectures. To attain such performance on real shared-memory machines, our algorithm computes convolutions converging o…
University of Wollongong（卧龙岗大学）；China University of Geosciences（中国地质大学）
Scene flow describes the motion of 3D objects in real world and potentially could be the basis of a good feature for 3D action recognition. However, its use for action recognition, especially in the context of convolutional neural networks (ConvNets), has not been previously studied. In this paper, we propose the extraction and use of scene flow for action recognition from RGB-D data. Previous works have considered the depth and RGB modalities as separate channels and extract features for later fusion. We take a different approach and consider the modalities as one entity, thus allowing featur…
