{"total":100,"rows":[{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294,"area":null},{"id":"2111.13587","title":"Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers","created":"2021-11-24","cited_by_count":248,"area":null},{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186,"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":"2203.04967","title":"UNeXt: MLP-based Rapid Medical Image Segmentation Network","created":"2022-03-09","cited_by_count":185,"area":null},{"id":"2204.03645","title":"DaViT: Dual Attention Vision Transformers","created":"2022-04-07","cited_by_count":175,"area":null},{"id":"2212.03145","title":"FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer","created":"2022-12-06","cited_by_count":133,"area":null},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132,"area":null},{"id":"2303.03667","title":"Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks","created":"2023-03-07","cited_by_count":130,"area":null},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126,"area":null},{"id":"2303.01480","title":"Delivering Arbitrary-Modal Semantic Segmentation","created":"2023-03-02","cited_by_count":117,"area":null},{"id":"2202.13556","title":"Filter-enhanced MLP is All You Need for Sequential Recommendation","created":"2022-02-28","cited_by_count":96,"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":"2203.01452","title":"Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation","created":"2022-03-02","cited_by_count":72,"area":null},{"id":"2111.11187","title":"PointMixer: MLP-Mixer for Point Cloud Understanding","created":"2021-11-22","cited_by_count":71,"area":null},{"id":"2206.10810","title":"A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift","created":"2022-06-22","cited_by_count":68,"area":null},{"id":"2108.13341","title":"Hire-MLP: Vision MLP via Hierarchical Rearrangement","created":"2021-08-30","cited_by_count":66,"area":null},{"id":"2111.04060","title":"Are we ready for a new paradigm shift? A Survey on Visual Deep MLP","created":"2021-11-07","cited_by_count":63,"area":null},{"id":"2111.12294","title":"An Image Patch is a Wave: Phase-Aware Vision MLP","created":"2021-11-24","cited_by_count":61,"area":null},{"id":"2304.06446","title":"SpectFormer: Frequency and Attention is what you need in a Vision Transformer","created":"2023-04-13","cited_by_count":48,"area":null},{"id":"2207.11860","title":"Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation","created":"2022-07-25","cited_by_count":46,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"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":"2303.01494","title":"Image as Set of Points","created":"2023-03-02","cited_by_count":43,"area":null},{"id":"2202.12165","title":"Transformers in Medical Image Analysis: A Review","created":"2022-02-24","cited_by_count":41,"area":null},{"id":"2109.04454","title":"ConvMLP: Hierarchical Convolutional MLPs for Vision","created":"2021-09-09","cited_by_count":37,"area":null},{"id":"2303.14124","title":"Towards Scalable Neural Representation for Diverse Videos","created":"2023-03-24","cited_by_count":37,"area":null},{"id":"2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","created":"2023-06-23","cited_by_count":37,"area":null},{"id":"2207.13159","title":"TINYCD: A (Not So) Deep Learning Model For Change Detection","created":"2022-07-26","cited_by_count":36,"area":null},{"id":"2211.14731","title":"BALF: Simple and Efficient Blur Aware Local Feature Detector","created":"2022-11-27","cited_by_count":34,"area":null},{"id":"2201.10801","title":"When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism","created":"2022-01-26","cited_by_count":30,"area":null},{"id":"2201.12083","title":"DynaMixer: A Vision MLP Architecture with Dynamic Mixing","created":"2022-01-28","cited_by_count":28,"area":null},{"id":"2303.11674","title":"ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalization","created":"2023-03-21","cited_by_count":28,"area":null},{"id":"2108.01072","title":"S$^2$-MLPv2: Improved Spatial-Shift MLP Architecture for Vision","created":"2021-08-02","cited_by_count":24,"area":null},{"id":"2205.01972","title":"Sequencer: Deep LSTM for Image Classification","created":"2022-05-04","cited_by_count":23,"area":null},{"id":"2305.12972","title":"VanillaNet: the Power of Minimalism in Deep Learning","created":"2023-05-22","cited_by_count":23,"area":null},{"id":"2111.12527","title":"MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning","created":"2021-11-24","cited_by_count":21,"area":null},{"id":"2205.10528","title":"PointVector: A Vector Representation In Point Cloud Analysis","created":"2022-05-21","cited_by_count":21,"area":null},{"id":"2206.06420","title":"GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation","created":"2022-06-13","cited_by_count":21,"area":null},{"id":"2305.00603","title":"Consolidator: Mergeable Adapter with Grouped Connections for Visual Adaptation","created":"2023-04-30","cited_by_count":18,"area":null},{"id":"2311.01310","title":"Scattering Vision Transformer: Spectral Mixing Matters","created":"2023-11-02","cited_by_count":17,"area":null},{"id":"2312.17276","title":"PanGu-$\\pi$: Enhancing Language Model Architectures via Nonlinearity Compensation","created":"2023-12-27","cited_by_count":17,"area":null},{"id":"2203.14679","title":"Brain-inspired Multilayer Perceptron with Spiking Neurons","created":"2022-03-28","cited_by_count":16,"area":null},{"id":"2304.13700","title":"UniNeXt: Exploring A Unified Architecture for Vision Recognition","created":"2023-04-26","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":"2203.03691","title":"HyperMixer: An MLP-based Low Cost Alternative to Transformers","created":"2022-03-07","cited_by_count":13,"area":null},{"id":"2210.02093","title":"Centralized Feature Pyramid for Object Detection","created":"2022-10-05","cited_by_count":13,"area":null},{"id":"2405.15365","title":"U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation","created":"2024-05-24","cited_by_count":13,"area":null},{"id":"2403.17409","title":"Neural Clustering based Visual Representation Learning","created":"2024-03-26","cited_by_count":12,"area":null},{"id":"2307.11342","title":"Tuning Pre-trained Model via Moment Probing","created":"2023-07-21","cited_by_count":9,"area":null},{"id":"2407.13108","title":"UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt","created":"2024-07-18","cited_by_count":8,"area":null},{"id":"2306.14525","title":"ParameterNet: Parameters Are All You Need","created":"2023-06-26","cited_by_count":7,"area":null},{"id":"2312.15681","title":"Partial Fine-Tuning: A Successor to Full Fine-Tuning for Vision Transformers","created":"2023-12-25","cited_by_count":7,"area":null},{"id":"2112.04453","title":"MLP Architectures for Vision-and-Language Modeling: An Empirical Study","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2202.06510","title":"Mixing and Shifting: Exploiting Global and Local Dependencies in Vision MLPs","created":"2022-02-14","cited_by_count":6,"area":null},{"id":"2203.06108","title":"Active Token Mixer","created":"2022-03-11","cited_by_count":6,"area":null},{"id":"2208.13138","title":"ClusTR: Exploring Efficient Self-attention via Clustering for Vision Transformers","created":"2022-08-28","cited_by_count":6,"area":null},{"id":"2302.08374","title":"Efficiency 360: Efficient Vision Transformers","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2108.04384","title":"RaftMLP: How Much Can Be Done Without Attention and with Less Spatial Locality?","created":"2021-08-09","cited_by_count":5,"area":null},{"id":"2201.09737","title":"RamanNet: A generalized neural network architecture for Raman Spectrum Analysis","created":"2022-01-20","cited_by_count":5,"area":null},{"id":"2208.11718","title":"gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","created":"2022-08-24","cited_by_count":5,"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":"2305.17644","title":"Caterpillar: A Pure-MLP Architecture with Shifted-Pillars-Concatenation","created":"2023-05-28","cited_by_count":4,"area":null},{"id":"2412.08341","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","created":"2024-12-11","cited_by_count":4,"area":null},{"id":"2201.00978","title":"PyramidTNT: Improved Transformer-in-Transformer Baselines with Pyramid Architecture","created":"2022-01-04","cited_by_count":3,"area":null},{"id":"2212.12552","title":"A Close Look at Spatial Modeling: From Attention to Convolution","created":"2022-12-23","cited_by_count":3,"area":null},{"id":"2212.14158","title":"BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons","created":"2022-12-29","cited_by_count":3,"area":null},{"id":"2303.13111","title":"Boosting Convolution with Efficient MLP-Permutation for Volumetric Medical Image Segmentation","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2406.09166","title":"Fine-Grained Domain Generalization with Feature Structuralization","created":"2024-06-13","cited_by_count":3,"area":null},{"id":"2407.02934","title":"PosMLP-Video: Spatial and Temporal Relative Position Encoding for Efficient Video Recognition","created":"2024-07-03","cited_by_count":3,"area":null},{"id":"2204.06779","title":"3D Shuffle-Mixer: An Efficient Context-Aware Vision Learner of Transformer-MLP Paradigm for Dense Prediction in Medical Volume","created":"2022-04-14","cited_by_count":2,"area":null},{"id":"2205.14477","title":"MDMLP: Image Classification from Scratch on Small Datasets with MLP","created":"2022-05-28","cited_by_count":2,"area":null},{"id":"2211.11085","title":"R2-MLP: Round-Roll MLP for Multi-View 3D Object Recognition","created":"2022-11-20","cited_by_count":2,"area":null},{"id":"2410.10914","title":"Towards Better Multi-head Attention via Channel-wise Sample Permutation","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2505.03113","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2207.07284","title":"Parameterization of Cross-Token Relations with Relative Positional Encoding for Vision MLP","created":"2022-07-15","cited_by_count":1,"area":null},{"id":"2208.11108","title":"Efficient Attention-free Video Shift Transformers","created":"2022-08-23","cited_by_count":1,"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":"2303.07726","title":"Good Neighbors Are All You Need for Chinese Grapheme-to-Phoneme Conversion","created":"2023-03-14","cited_by_count":1,"area":null},{"id":"2304.12615","title":"STM-UNet: An Efficient U-shaped Architecture Based on Swin Transformer and Multi-scale MLP for Medical Image Segmentation","created":"2023-04-25","cited_by_count":1,"area":null},{"id":"2305.14675","title":"TriMLP: Revenge of a MLP-like Architecture in Sequential Recommendation","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2311.13263","title":"CMFDFormer: Transformer-based Copy-Move Forgery Detection with Continual Learning","created":"2023-11-22","cited_by_count":1,"area":null},{"id":"2312.05832","title":"Spatial-wise Dynamic Distillation for MLP-like Efficient Visual Fault Detection of Freight Trains","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2404.00648","title":"SpiralMLP: A Lightweight Vision MLP Architecture","created":"2024-03-31","cited_by_count":1,"area":null},{"id":"2601.03056","title":"Fine-Grained Generalization via Structuralizing Concept and Feature Space into Commonality, Specificity and Confounding","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2207.10255","title":"SplitMixer: Fat Trimmed From MLP-like Models","created":"2022-07-21","cited_by_count":0,"area":null},{"id":"2208.08191","title":"Transformer Vs. MLP-Mixer: Exponential Expressive Gap For NLP Problems","created":"2022-08-17","cited_by_count":0,"area":null},{"id":"2210.12361","title":"MS-DCANet: A Novel Segmentation Network For Multi-Modality COVID-19 Medical Images","created":"2022-10-22","cited_by_count":0,"area":null},{"id":"2211.14434","title":"Multi-Step Short-Term Wind Speed Prediction with Rank Pooling and Fast Fourier Transformation","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2304.03917","title":"MC-MLP:Multiple Coordinate Frames in all-MLP Architecture for Vision","created":"2023-04-08","cited_by_count":0,"area":null},{"id":"2308.13363","title":"CS-Mixer: A Cross-Scale Vision MLP Model with Spatial-Channel Mixing","created":"2023-08-25","cited_by_count":0,"area":null},{"id":"2309.06721","title":"Dynamic Spectrum Mixer for Visual Recognition","created":"2023-09-13","cited_by_count":0,"area":null},{"id":"2311.18735","title":"Dimension Mixer: Group Mixing of Input Dimensions for Efficient Function Approximation","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2402.17370","title":"An Efficient MLP-based Point-guided Segmentation Network for Ore Images with Ambiguous Boundary","created":"2024-02-27","cited_by_count":0,"area":null},{"id":"2405.18849","title":"SFANet: Spatial-Frequency Attention Network for Weather Forecasting","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2408.13661","title":"Hierarchical Network Fusion for Multi-Modal Electron Micrograph Representation Learning with Foundational Large Language Models","created":"2024-08-24","cited_by_count":0,"area":null},{"id":"2411.18995","title":"MVFormer: Diversifying Feature Normalization and Token Mixing for Efficient Vision Transformers","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2506.10084","title":"DeepTraverse: A Depth-First Search Inspired Network for Algorithmic Visual Understanding","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2506.21682","title":"Do We Really Need GNNs with Explicit Structural Modeling? MLPs Suffice for Language Model Representations","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2607.06949","title":"SpiS-GAN: Spiral-Modulated Handwriting Synthesis with Star Operation","created":"2026-07-08","cited_by_count":0,"area":null}],"next_cursor":null}