# Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations Source: [Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations]() Collection index: [llms.txt]() Data updated: 2025-10-26T03:27:16.108Z Authors: Yiyuan Zhang, Xiaohan Ding, Xiangyu Yue Published: 2024-10-10T15:43:55.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on COCO](): Object Detection; COCO; AP (Box): 53. - [Image Classification on ImageNet-1K (val) (Accuracy)](): Image Classification; ImageNet-1k (val); Top-1 Accuracy: 83.9. - [Semantic Segmentation on ADE20K (val)](): Semantic segmentation; ADE20K (val); mIoU: 48.6. ## Original sources and implementation [Original paper]() [PDF]()