{"total":192,"rows":[{"id":"2402.02366","title":"Transolver: A Fast Transformer Solver for PDEs on General Geometries","created":"2024-02-04","cited_by_count":326,"area":null},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241,"area":null},{"id":"2206.00272","title":"Vision GNN: An Image is Worth Graph of Nodes","created":"2022-06-01","cited_by_count":186,"area":null},{"id":"2204.03645","title":"DaViT: Dual Attention Vision Transformers","created":"2022-04-07","cited_by_count":175,"area":null},{"id":"2303.14189","title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","created":"2023-03-24","cited_by_count":162,"area":null},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155,"area":null},{"id":"2206.09959","title":"Global Context Vision Transformers","created":"2022-06-20","cited_by_count":98,"area":null},{"id":"2210.09221","title":"Vision Transformers provably learn spatial structure","created":"2022-10-13","cited_by_count":93,"area":null},{"id":"2303.01870","title":"Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models","created":"2023-03-03","cited_by_count":79,"area":null},{"id":"2407.05848","title":"Wavelet Convolutions for Large Receptive Fields","created":"2024-07-08","cited_by_count":74,"area":null},{"id":"2206.10555","title":"LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs","created":"2022-06-21","cited_by_count":72,"area":null},{"id":"2203.11335","title":"Global Matching with Overlapping Attention for Optical Flow Estimation","created":"2022-03-21","cited_by_count":64,"area":null},{"id":"2304.05366","title":"The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning","created":"2023-04-11","cited_by_count":63,"area":null},{"id":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62,"area":null},{"id":"2205.02719","title":"Communication-Efficient Adaptive Federated Learning","created":"2022-05-05","cited_by_count":55,"area":null},{"id":"2210.02984","title":"The Lie Derivative for Measuring Learned Equivariance","created":"2022-10-06","cited_by_count":54,"area":null},{"id":"2305.09828","title":"Mimetic Initialization of Self-Attention Layers","created":"2023-05-16","cited_by_count":54,"area":null},{"id":"2306.11249","title":"OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning","created":"2023-06-20","cited_by_count":54,"area":null},{"id":"2403.07592","title":"Accurate Spatial Gene Expression Prediction by integrating Multi-resolution features","created":"2024-03-12","cited_by_count":52,"area":null},{"id":"2407.03653","title":"reBEN: Refined BigEarthNet Dataset for Remote Sensing Image Analysis","created":"2024-07-04","cited_by_count":48,"area":null},{"id":"2205.15175","title":"ShuffleMixer: An Efficient ConvNet for Image Super-Resolution","created":"2022-05-30","cited_by_count":45,"area":null},{"id":"2303.01494","title":"Image as Set of Points","created":"2023-03-02","cited_by_count":43,"area":null},{"id":"2303.02970","title":"Rethinking Confidence Calibration for Failure Prediction","created":"2023-03-06","cited_by_count":43,"area":null},{"id":"2210.06441","title":"How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization","created":"2022-10-12","cited_by_count":40,"area":null},{"id":"2208.03160","title":"Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks","created":"2022-08-05","cited_by_count":39,"area":null},{"id":"2206.03452","title":"Can CNNs Be More Robust Than Transformers?","created":"2022-06-07","cited_by_count":38,"area":null},{"id":"2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","created":"2023-06-23","cited_by_count":37,"area":null},{"id":"2206.01136","title":"Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives","created":"2022-06-02","cited_by_count":33,"area":null},{"id":"2308.01239","title":"CMUNeXt: An Efficient Medical Image Segmentation Network based on Large Kernel and Skip Fusion","created":"2023-08-02","cited_by_count":31,"area":null},{"id":"2203.08147","title":"Energy-Latency Attacks via Sponge Poisoning","created":"2022-03-14","cited_by_count":29,"area":null},{"id":"2210.13012","title":"CMU-Net: A Strong ConvMixer-based Medical Ultrasound Image Segmentation Network","created":"2022-10-24","cited_by_count":29,"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":"2211.12509","title":"SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning","created":"2022-11-22","cited_by_count":22,"area":null},{"id":"2305.01604","title":"The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold","created":"2023-05-02","cited_by_count":21,"area":null},{"id":"2310.00655","title":"PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting","created":"2023-10-01","cited_by_count":20,"area":null},{"id":"2205.14375","title":"WaveMix: A Resource-efficient Neural Network for Image Analysis","created":"2022-05-28","cited_by_count":19,"area":null},{"id":"2304.03977","title":"EMP-SSL: Towards Self-Supervised Learning in One Training Epoch","created":"2023-04-08","cited_by_count":19,"area":null},{"id":"2207.11240","title":"Discrete Key-Value Bottleneck","created":"2022-07-22","cited_by_count":18,"area":null},{"id":"2204.07707","title":"Privacy-Preserving Image Classification Using Isotropic Network","created":"2022-04-16","cited_by_count":17,"area":null},{"id":"2412.02601","title":"MERGE: Multi-faceted Hierarchical Graph-based GNN for Gene Expression Prediction from Whole Slide Histopathology Images","created":"2024-12-03","cited_by_count":17,"area":null},{"id":"2210.03651","title":"Understanding the Covariance Structure of Convolutional Filters","created":"2022-10-07","cited_by_count":16,"area":null},{"id":"2210.05960","title":"Efficient Image Super-Resolution using Vast-Receptive-Field Attention","created":"2022-10-12","cited_by_count":16,"area":null},{"id":"2403.19963","title":"Efficient Modulation for Vision Networks","created":"2024-03-29","cited_by_count":16,"area":null},{"id":"2504.08710","title":"Hypergraph Vision Transformers: Images are More than Nodes, More than Edges","created":"2025-04-11","cited_by_count":16,"area":null},{"id":"2208.02019","title":"YOLO-FaceV2: A Scale and Occlusion Aware Face Detector","created":"2022-08-03","cited_by_count":15,"area":null},{"id":"2306.16103","title":"1M parameters are enough? A lightweight CNN-based model for medical image segmentation","created":"2023-06-28","cited_by_count":15,"area":null},{"id":"2407.06076","title":"Understanding Visual Feature Reliance through the Lens of Complexity","created":"2024-07-08","cited_by_count":15,"area":null},{"id":"2308.03172","title":"Two Sides of Miscalibration: Identifying Over and Under-Confidence Prediction for Network Calibration","created":"2023-08-06","cited_by_count":14,"area":null},{"id":"2403.06925","title":"Transformers Learn Low Sensitivity Functions: Investigations and Implications","created":"2024-03-11","cited_by_count":14,"area":null},{"id":"2202.09745","title":"RDP-Net: Region Detail Preserving Network for Change Detection","created":"2022-02-20","cited_by_count":13,"area":null},{"id":"2208.09378","title":"Labeling Chaos to Learning Harmony: Federated Learning with Noisy Labels","created":"2022-08-19","cited_by_count":13,"area":null},{"id":"2505.01996","title":"Always Skip Attention","created":"2025-05-04","cited_by_count":13,"area":null},{"id":"2506.09784","title":"Accurate and efficient zero-shot 6D pose estimation with frozen foundation models","created":"2025-06-11","cited_by_count":13,"area":null},{"id":"2509.20234","title":"ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression","created":"2025-09-24","cited_by_count":13,"area":null},{"id":"2207.05366","title":"Image and Model Transformation with Secret Key for Vision Transformer","created":"2022-07-12","cited_by_count":12,"area":null},{"id":"2304.03282","title":"Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention","created":"2023-04-06","cited_by_count":12,"area":null},{"id":"2401.17992","title":"Multilinear Operator Networks","created":"2024-01-31","cited_by_count":12,"area":null},{"id":"2403.17409","title":"Neural Clustering based Visual Representation Learning","created":"2024-03-26","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":"2203.11987","title":"PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers","created":"2022-03-22","cited_by_count":11,"area":null},{"id":"2303.11934","title":"Sparse Distributed Memory is a Continual Learner","created":"2023-03-20","cited_by_count":11,"area":null},{"id":"2206.08954","title":"Bag of Image Patch Embedding Behind the Success of Self-Supervised Learning","created":"2022-06-17","cited_by_count":10,"area":null},{"id":"2302.09738","title":"Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning","created":"2023-02-20","cited_by_count":10,"area":null},{"id":"2310.01365","title":"Elephant Neural Networks: Born to Be a Continual Learner","created":"2023-10-02","cited_by_count":10,"area":null},{"id":"2203.03689","title":"WaveMix: Resource-efficient Token Mixing for Images","created":"2022-03-07","cited_by_count":9,"area":null},{"id":"2210.06699","title":"Parameter-Efficient Masking Networks","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2302.02234","title":"Revisiting Image Deblurring with an Efficient ConvNet","created":"2023-02-04","cited_by_count":9,"area":null},{"id":"2303.12669","title":"An Extended Study of Human-like Behavior under Adversarial Training","created":"2023-03-22","cited_by_count":9,"area":null},{"id":"2305.10455","title":"Towards Generalist Robots: A Promising Paradigm via Generative Simulation","created":"2023-05-17","cited_by_count":9,"area":null},{"id":"2312.05705","title":"Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC","created":"2023-12-09","cited_by_count":9,"area":null},{"id":"2211.14425","title":"PatchGT: Transformer over Non-trainable Clusters for Learning Graph Representations","created":"2022-11-26","cited_by_count":8,"area":null},{"id":"2310.15165","title":"Handling Data Heterogeneity via Architectural Design for Federated Visual Recognition","created":"2023-10-23","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":"2501.07930","title":"An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2206.08298","title":"Video Capsule Endoscopy Classification using Focal Modulation Guided Convolutional Neural Network","created":"2022-06-16","cited_by_count":7,"area":null},{"id":"2207.08148","title":"Improving Deep Neural Network Random Initialization Through Neuronal Rewiring","created":"2022-07-17","cited_by_count":7,"area":null},{"id":"2310.17645","title":"PubDef: Defending Against Transfer Attacks From Public Models","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2405.11180","title":"GestFormer: Multiscale Wavelet Pooling Transformer Network for Dynamic Hand Gesture Recognition","created":"2024-05-18","cited_by_count":7,"area":null},{"id":"2509.06467","title":"Does DINOv3 Set a New Medical Vision Standard? Benchmarking 2D and 3D Classification, Segmentation, and Registration","created":"2025-09-08","cited_by_count":7,"area":null},{"id":"2204.07673","title":"Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations","created":"2022-04-15","cited_by_count":6,"area":null},{"id":"2208.13571","title":"PECAN: A Product-Quantized Content Addressable Memory Network","created":"2022-08-13","cited_by_count":6,"area":null},{"id":"2210.05657","title":"The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes","created":"2022-10-11","cited_by_count":6,"area":null},{"id":"2401.07579","title":"PMFSNet: Polarized Multi-scale Feature Self-attention Network For Lightweight Medical Image Segmentation","created":"2024-01-15","cited_by_count":6,"area":null},{"id":"2401.14469","title":"Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels","created":"2024-01-25","cited_by_count":6,"area":null},{"id":"2502.00571","title":"Contrastive Forward-Forward: A Training Algorithm of Vision Transformer","created":"2025-02-01","cited_by_count":6,"area":null},{"id":"2505.19985","title":"Structured Initialization for Vision Transformers","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2201.10271","title":"Convolutional Xformers for Vision","created":"2022-01-25","cited_by_count":5,"area":null},{"id":"2206.08558","title":"How You Start Matters for Generalization","created":"2022-06-17","cited_by_count":5,"area":null},{"id":"2209.06383","title":"Analysis of Quantization on MLP-based Vision Models","created":"2022-09-14","cited_by_count":5,"area":null},{"id":"2210.04303","title":"Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap","created":"2022-10-09","cited_by_count":5,"area":null},{"id":"2305.17190","title":"Multiplication-Free Transformer Training via Piecewise Affine Operations","created":"2023-05-26","cited_by_count":5,"area":null},{"id":"2306.03406","title":"Deep neural networks architectures from the perspective of manifold learning","created":"2023-06-06","cited_by_count":5,"area":null},{"id":"2402.17853","title":"Latent Neural PDE Solver: a reduced-order modelling framework for partial differential equations","created":"2024-02-27","cited_by_count":5,"area":null},{"id":"2405.15405","title":"Transformer-based Federated Learning for Multi-Label Remote Sensing Image Classification","created":"2024-05-24","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":"2209.06953","title":"On the interplay of adversarial robustness and architecture components: patches, convolution and attention","created":"2022-09-14","cited_by_count":4,"area":null},{"id":"2210.11407","title":"Similarity of Neural Architectures using Adversarial Attack Transferability","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2212.06595","title":"OAMixer: Object-aware Mixing Layer for Vision Transformers","created":"2022-12-13","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":"2305.08826","title":"Learning Better Contrastive View from Radiologist's Gaze","created":"2023-05-15","cited_by_count":4,"area":null}],"next_cursor":"100"}