{"total":130,"rows":[{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969,"area":null},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482,"area":null},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132,"area":null},{"id":"2303.09030","title":"Large Selective Kernel Network for Remote Sensing Object Detection","created":"2023-03-16","cited_by_count":98,"area":null},{"id":"2210.00077","title":"E-Branchformer: Branchformer with Enhanced merging for speech recognition","created":"2022-09-30","cited_by_count":92,"area":null},{"id":"2303.16900","title":"InceptionNeXt: When Inception Meets ConvNeXt","created":"2023-03-29","cited_by_count":86,"area":null},{"id":"2211.11943","title":"Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition","created":"2022-11-22","cited_by_count":81,"area":null},{"id":"2407.05848","title":"Wavelet Convolutions for Large Receptive Fields","created":"2024-07-08","cited_by_count":74,"area":null},{"id":"2311.15599","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","created":"2023-11-27","cited_by_count":64,"area":null},{"id":"2311.17132","title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers","created":"2023-11-28","cited_by_count":61,"area":null},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2412.05270","title":"APOLLO: SGD-like Memory, AdamW-level Performance","created":"2024-12-06","cited_by_count":54,"area":null},{"id":"2403.06258","title":"Poly Kernel Inception Network for Remote Sensing Detection","created":"2024-03-10","cited_by_count":52,"area":null},{"id":"2307.14008","title":"Adaptive Frequency Filters As Efficient Global Token Mixers","created":"2023-07-26","cited_by_count":45,"area":null},{"id":"2403.11735","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","created":"2024-03-18","cited_by_count":44,"area":null},{"id":"2407.08296","title":"Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients","created":"2024-07-11","cited_by_count":38,"area":null},{"id":"2411.04732","title":"Convolutional Differentiable Logic Gate Networks","created":"2024-11-07","cited_by_count":37,"area":null},{"id":"2412.13795","title":"Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN","created":"2024-12-18","cited_by_count":37,"area":null},{"id":"2403.05369","title":"Frequency-Adaptive Dilated Convolution for Semantic Segmentation","created":"2024-03-08","cited_by_count":34,"area":null},{"id":"2302.06492","title":"Optical flow estimation from event-based cameras and spiking neural networks","created":"2023-02-13","cited_by_count":33,"area":null},{"id":"2403.07589","title":"PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution","created":"2024-03-12","cited_by_count":28,"area":null},{"id":"2303.16094","title":"LinK: Linear Kernel for LiDAR-based 3D Perception","created":"2023-03-28","cited_by_count":26,"area":null},{"id":"2309.01439","title":"Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN","created":"2023-09-04","cited_by_count":25,"area":null},{"id":"2502.20087","title":"OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels","created":"2025-02-27","cited_by_count":25,"area":null},{"id":"2303.03932","title":"FFT-based Dynamic Token Mixer for Vision","created":"2023-03-07","cited_by_count":22,"area":null},{"id":"2210.05950","title":"ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors","created":"2022-10-12","cited_by_count":21,"area":null},{"id":"2309.01430","title":"DAT++: Spatially Dynamic Vision Transformer with Deformable Attention","created":"2023-09-04","cited_by_count":21,"area":null},{"id":"2310.19380","title":"TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition","created":"2023-10-30","cited_by_count":21,"area":null},{"id":"2301.11329","title":"Anatomy-aware and acquisition-agnostic joint registration with SynthMorph","created":"2023-01-26","cited_by_count":19,"area":null},{"id":"2305.19454","title":"Dynamic Sparsity Is Channel-Level Sparsity Learner","created":"2023-05-30","cited_by_count":18,"area":null},{"id":"2210.03651","title":"Understanding the Covariance Structure of Convolutional Filters","created":"2022-10-07","cited_by_count":16,"area":null},{"id":"2312.04727","title":"E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation","created":"2023-12-07","cited_by_count":16,"area":null},{"id":"2401.15235","title":"CascadedGaze: Efficiency in Global Context Extraction for Image Restoration","created":"2024-01-26","cited_by_count":16,"area":null},{"id":"2403.15173","title":"LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels","created":"2024-03-22","cited_by_count":15,"area":null},{"id":"2303.02165","title":"DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network","created":"2023-03-05","cited_by_count":14,"area":null},{"id":"2501.03775","title":"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection","created":"2025-01-07","cited_by_count":14,"area":null},{"id":"2503.07499","title":"AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements","created":"2025-03-10","cited_by_count":14,"area":null},{"id":"2401.05633","title":"Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach","created":"2024-01-11","cited_by_count":13,"area":null},{"id":"2405.18425","title":"ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2406.02395","title":"GrootVL: Tree Topology is All You Need in State Space Model","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2303.05785","title":"Scaling Up 3D Kernels with Bayesian Frequency Re-parameterization for Medical Image Segmentation","created":"2023-03-10","cited_by_count":12,"area":null},{"id":"2310.05026","title":"Low-Resolution Self-Attention for Semantic Segmentation","created":"2023-10-08","cited_by_count":12,"area":null},{"id":"2403.19588","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","created":"2024-03-28","cited_by_count":12,"area":null},{"id":"2410.03030","title":"Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness","created":"2024-10-03","cited_by_count":11,"area":null},{"id":"2407.05169","title":"DehazeDCT: Towards Effective Non-Homogeneous Dehazing via Deformable Convolutional Transformer","created":"2024-05-24","cited_by_count":10,"area":null},{"id":"2302.02234","title":"Revisiting Image Deblurring with an Efficient ConvNet","created":"2023-02-04","cited_by_count":9,"area":null},{"id":"2310.10563","title":"RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2403.10674","title":"D-Net: Dynamic Large Kernel with Dynamic Feature Fusion for Volumetric Medical Image Segmentation","created":"2024-03-15","cited_by_count":9,"area":null},{"id":"2403.19490","title":"Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment","created":"2024-03-28","cited_by_count":9,"area":null},{"id":"2407.14340","title":"Large Kernel Distillation Network for Efficient Single Image Super-Resolution","created":"2024-07-19","cited_by_count":9,"area":null},{"id":"2502.12627","title":"DAMamba: Vision State Space Model with Dynamic Adaptive Scan","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2303.11525","title":"Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency","created":"2023-03-21","cited_by_count":8,"area":null},{"id":"2307.10001","title":"As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain","created":"2023-07-19","cited_by_count":8,"area":null},{"id":"2311.17524","title":"Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context","created":"2023-11-29","cited_by_count":8,"area":null},{"id":"2406.04330","title":"Parameter-Inverted Image Pyramid Networks","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2407.08972","title":"Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness","created":"2024-07-12","cited_by_count":8,"area":null},{"id":"2410.08049","title":"Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2501.07783","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2211.05781","title":"Demystify Transformers & Convolutions in Modern Image Deep Networks","created":"2022-11-10","cited_by_count":7,"area":null},{"id":"2404.11848","title":"Partial Large Kernel CNNs for Efficient Super-Resolution","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2304.02330","title":"SMPConv: Self-moving Point Representations for Continuous Convolution","created":"2023-04-05","cited_by_count":6,"area":null},{"id":"2306.06365","title":"FalconNet: Factorization for the Light-weight ConvNets","created":"2023-06-10","cited_by_count":6,"area":null},{"id":"2308.07251","title":"Large-kernel Attention for Efficient and Robust Brain Lesion Segmentation","created":"2023-08-14","cited_by_count":5,"area":null},{"id":"2405.12721","title":"StarLKNet: Star Mixup with Large Kernel Networks for Palm Vein Identification","created":"2024-05-21","cited_by_count":5,"area":null},{"id":"2503.06671","title":"Emulating Self-attention with Convolution for Efficient Image Super-Resolution","created":"2025-03-09","cited_by_count":5,"area":null},{"id":"2504.10795","title":"3D Wavelet Convolutions with Extended Receptive Fields for Hyperspectral Image Classification","created":"2025-04-15","cited_by_count":5,"area":null},{"id":"2211.07157","title":"ParCNetV2: Oversized Kernel with Enhanced Attention","created":"2022-11-14","cited_by_count":4,"area":null},{"id":"2301.03169","title":"A Study on the Generality of Neural Network Structures for Monocular Depth Estimation","created":"2023-01-09","cited_by_count":4,"area":null},{"id":"2301.11360","title":"The Power of Linear Combinations: Learning with Random Convolutions","created":"2023-01-26","cited_by_count":4,"area":null},{"id":"2305.17644","title":"Caterpillar: A Pure-MLP Architecture with Shifted-Pillars-Concatenation","created":"2023-05-28","cited_by_count":4,"area":null},{"id":"2401.11859","title":"LKFormer: Large Kernel Transformer for Infrared Image Super-Resolution","created":"2024-01-22","cited_by_count":4,"area":null},{"id":"2401.12736","title":"$ShiftwiseConv:$ Small Convolutional Kernel with Large Kernel Effect","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2406.16004","title":"RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization","created":"2024-06-23","cited_by_count":4,"area":null},{"id":"2410.08582","title":"DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention","created":"2024-10-11","cited_by_count":4,"area":null},{"id":"2501.19107","title":"Brain network science modelling of sparse neural networks enables Transformers and LLMs to perform as fully connected","created":"2025-01-31","cited_by_count":4,"area":null},{"id":"2307.11862","title":"Digital Modeling on Large Kernel Metamaterial Neural Network","created":"2023-07-21","cited_by_count":3,"area":null},{"id":"2309.15812","title":"Convolutional Networks with Oriented 1D Kernels","created":"2023-09-27","cited_by_count":3,"area":null},{"id":"2504.02440","title":"HGFormer: Topology-Aware Vision Transformer with HyperGraph Learning","created":"2025-04-03","cited_by_count":3,"area":null},{"id":"2508.09000","title":"UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2508.11893","title":"Large Kernel Modulation Network for Efficient Image Super-Resolution","created":"2025-08-16","cited_by_count":3,"area":null},{"id":"2302.04544","title":"GMConv: Modulating Effective Receptive Fields for Convolutional Kernels","created":"2023-02-09","cited_by_count":2,"area":null},{"id":"2304.02860","title":"Towards an Effective and Efficient Transformer for Rain-by-snow Weather Removal","created":"2023-04-06","cited_by_count":2,"area":null},{"id":"2304.03812","title":"High-order Spatial Interactions Enhanced Lightweight Model for Optical Remote Sensing Image-based Small Ship Detection","created":"2023-04-07","cited_by_count":2,"area":null},{"id":"2312.13735","title":"DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2402.19305","title":"HyenaPixel: Global Image Context with Convolutions","created":"2024-02-29","cited_by_count":2,"area":null},{"id":"2403.06676","title":"CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2405.13972","title":"Infinite-Dimensional Feature Interaction","created":"2024-05-22","cited_by_count":2,"area":null},{"id":"2406.08782","title":"Hybrid Spatial-spectral Neural Network for Hyperspectral Image Denoising","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2408.09453","title":"Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling","created":"2024-08-18","cited_by_count":2,"area":null},{"id":"2411.06236","title":"Zero-Shot NAS via the Suppression of Local Entropy Decrease","created":"2024-11-09","cited_by_count":2,"area":null},{"id":"2505.24037","title":"Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2301.08868","title":"Computationally Efficient 3D MRI Reconstruction with Adaptive MLP","created":"2023-01-21","cited_by_count":1,"area":null},{"id":"2310.16483","title":"Gramian Attention Heads are Strong yet Efficient Vision Learners","created":"2023-10-25","cited_by_count":1,"area":null},{"id":"2311.12956","title":"Innovative Horizons in Aerial Imagery: LSKNet Meets DiffusionDet for Advanced Object Detection","created":"2023-11-21","cited_by_count":1,"area":null},{"id":"2406.02021","title":"FFNet: MetaMixer-based Efficient Convolutional Mixer Design","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2411.10198","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","created":"2024-11-15","cited_by_count":1,"area":null},{"id":"2507.22407","title":"Moir\\'e Zero: An Efficient and High-Performance Neural Architecture for Moir\\'e Removal","created":"2025-07-30","cited_by_count":1,"area":null},{"id":"2601.22095","title":"GeoNorm: Unify Pre-Norm and Post-Norm with Geodesic Optimization","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.04170","title":"Partial Ring Scan: Revisiting Scan Order in Vision State Space Models","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2603.10834","title":"On the Reliability of Cue Conflict and Beyond","created":"2026-03-11","cited_by_count":1,"area":null}],"next_cursor":"100"}