# UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition

arXiv: https://arxiv.org/abs/2311.15599 · HTML: https://mlsanity.com/paper/2311.15599/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- Builds on 78 of its 101 references that are in the map.
- First posted on arXiv 27 Nov 2023.

## Builds on (most cited first, 30 of 78)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)

## Built on by (most cited first, 30 of 64)

- [Timer-XL: Long-Context Transformers for Unified Time Series Forecasting](https://mlsanity.com/paper/2410.04803/) (2024)
- [OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels](https://mlsanity.com/paper/2502.20087/) (2025)
- [Frequency Dynamic Convolution for Dense Image Prediction](https://mlsanity.com/paper/2503.18783/) (2025)
- [Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines](https://mlsanity.com/paper/2410.21220/) (2024)
- [LSNet: See Large, Focus Small](https://mlsanity.com/paper/2503.23135/) (2025)
- [Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection](https://mlsanity.com/paper/2501.03775/) (2025)
- [GrootVL: Tree Topology is All You Need in State Space Model](https://mlsanity.com/paper/2406.02395/) (2024)
- [ScaleKD: Strong Vision Transformers Could Be Excellent Teachers](https://mlsanity.com/paper/2411.06786/) (2024)
- [RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion](https://mlsanity.com/paper/2407.21631/) (2024)
- [DAMamba: Vision State Space Model with Dynamic Adaptive Scan](https://mlsanity.com/paper/2502.12627/) (2025)
- [Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness](https://mlsanity.com/paper/2407.08972/) (2024)
- [Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations](https://mlsanity.com/paper/2410.08049/) (2024)
- [Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities](https://mlsanity.com/paper/2401.14405/) (2024)
- [Partial Large Kernel CNNs for Efficient Super-Resolution](https://mlsanity.com/paper/2404.11848/) (2024)
- [Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Booster](https://mlsanity.com/paper/2506.18034/) (2025)
- [DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling](https://mlsanity.com/paper/2505.11196/) (2025)
- [StarLKNet: Star Mixup with Large Kernel Networks for Palm Vein Identification](https://mlsanity.com/paper/2405.12721/) (2024)
- [Explore the Limits of Omni-modal Pretraining at Scale](https://mlsanity.com/paper/2406.09412/) (2024)
- [ShiftwiseConv: Small Convolutional Kernel with Large Kernel Effect](https://mlsanity.com/paper/2401.12736/) (2024)
- [RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization](https://mlsanity.com/paper/2406.16004/) (2024)
- [DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention](https://mlsanity.com/paper/2410.08582/) (2024)
- [InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions](https://mlsanity.com/paper/2402.03040/) (2024)
- [MiniMaxAD: A Lightweight Autoencoder for Feature-Rich Anomaly Detection](https://mlsanity.com/paper/2405.09933/) (2024)
- [LKCell: Efficient Cell Nuclei Instance Segmentation with Large Convolution Kernels](https://mlsanity.com/paper/2407.18054/) (2024)
- [Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning](https://mlsanity.com/paper/2410.06373/) (2024)
- [UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale](https://mlsanity.com/paper/2508.09000/) (2025)
- [AWM-Fuse: Multi-Modality Image Fusion for Adverse Weather via Global and Local Text Perception](https://mlsanity.com/paper/2508.16881/) (2025)
- [RCTDistill: Cross-Modal Knowledge Distillation Framework for Radar-Camera 3D Object Detection with Temporal Fusion](https://mlsanity.com/paper/2509.17712/) (2025)
- [MMDrive: Interactive Scene Understanding Beyond Vision with Multi-representational Fusion](https://mlsanity.com/paper/2512.13177/) (2025)
- [DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation](https://mlsanity.com/paper/2312.13735/) (2023)

## Abstract (arXiv)

Large-kernel convolutional neural networks (ConvNets) have recently received extensive research attention, but two unresolved and critical issues demand further investigation. 1) The architectures of existing large-kernel ConvNets largely follow the design principles of conventional ConvNets or transformers, while the architectural design for large-kernel ConvNets remains under-addressed. 2) As transformers have dominated multiple modalities, it remains to be investigated whether ConvNets also have a strong universal perception ability in domains beyond vision. In this paper, we contribute from two aspects. 1) We propose four architectural guidelines for designing large-kernel ConvNets, the core of which is to exploit the essential characteristics of large kernels that distinguish them from small kernels - they can see wide without going deep. Following such guidelines, our proposed large-kernel ConvNet shows leading performance in image recognition (ImageNet accuracy of 88.0%, ADE20K mIoU of 55.6%, and COCO box AP of 56.4%), demonstrating better performance and higher speed than the recent powerful competitors. 2) We discover large kernels are the key to unlocking the exceptional performance of ConvNets in domains where they were originally not proficient. With certain modality-related preprocessing approaches, the proposed model achieves state-of-the-art performance on time-series forecasting and audio recognition tasks even without modality-specific customization to the architecture. All the code and models are publicly available on GitHub and Huggingface.