{"total":91,"rows":[{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815,"area":null},{"id":"2203.06697","title":"Efficient Long-Range Attention Network for Image Super-resolution","created":"2022-03-13","cited_by_count":151,"area":null},{"id":"2107.08391","title":"AS-MLP: An Axial Shifted MLP Architecture for Vision","created":"2021-07-18","cited_by_count":101,"area":null},{"id":"2106.05968","title":"Space-time Mixing Attention for Video Transformer","created":"2021-06-10","cited_by_count":84,"area":null},{"id":"2106.07477","title":"S$^2$-MLP: Spatial-Shift MLP Architecture for Vision","created":"2021-06-14","cited_by_count":83,"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":"2108.02432","title":"Token Shift Transformer for Video Classification","created":"2021-08-05","cited_by_count":61,"area":null},{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56,"area":null},{"id":"2203.10681","title":"Online Continual Learning for Embedded Devices","created":"2022-03-21","cited_by_count":49,"area":null},{"id":"2111.08446","title":"Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directions","created":"2021-11-03","cited_by_count":43,"area":null},{"id":"2112.07957","title":"FEAR: Fast, Efficient, Accurate and Robust Visual Tracker","created":"2021-12-15","cited_by_count":38,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38,"area":null},{"id":"2107.13046","title":"MixFaceNets: Extremely Efficient Face Recognition Networks","created":"2021-07-27","cited_by_count":36,"area":null},{"id":"2210.03230","title":"NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies","created":"2022-10-06","cited_by_count":36,"area":null},{"id":"2307.01838","title":"EdgeFace: Efficient Face Recognition Model for Edge Devices","created":"2023-07-04","cited_by_count":33,"area":null},{"id":"2110.13041","title":"Applications and Techniques for Fast Machine Learning in Science","created":"2021-10-25","cited_by_count":32,"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":"2406.05981","title":"ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization","created":"2024-06-10","cited_by_count":30,"area":null},{"id":"2110.10538","title":"ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning","created":"2021-10-20","cited_by_count":29,"area":null},{"id":"2108.05009","title":"Learning Deep Multimodal Feature Representation with Asymmetric Multi-layer Fusion","created":"2021-08-11","cited_by_count":25,"area":null},{"id":"2206.00843","title":"DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks","created":"2022-06-02","cited_by_count":19,"area":null},{"id":"2407.03197","title":"DyFADet: Dynamic Feature Aggregation for Temporal Action Detection","created":"2024-07-03","cited_by_count":19,"area":null},{"id":"2302.11974","title":"LightCTS: A Lightweight Framework for Correlated Time Series Forecasting","created":"2023-02-23","cited_by_count":18,"area":null},{"id":"2308.02066","title":"Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives","created":"2023-08-03","cited_by_count":18,"area":null},{"id":"2109.13227","title":"TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device","created":"2021-09-27","cited_by_count":17,"area":null},{"id":"2106.08630","title":"HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning","created":"2021-06-16","cited_by_count":16,"area":null},{"id":"2106.14882","title":"Rethinking Token-Mixing MLP for MLP-based Vision Backbone","created":"2021-06-28","cited_by_count":15,"area":null},{"id":"2201.03297","title":"GhostNets on Heterogeneous Devices via Cheap Operations","created":"2022-01-10","cited_by_count":15,"area":null},{"id":"2103.14158","title":"InversionNet3D: Efficient and Scalable Learning for 3D Full Waveform Inversion","created":"2021-03-25","cited_by_count":13,"area":null},{"id":"2105.07085","title":"MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations","created":"2021-05-14","cited_by_count":13,"area":null},{"id":"2412.09895","title":"Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP","created":"2024-12-13","cited_by_count":9,"area":null},{"id":"2101.08525","title":"GhostSR: Learning Ghost Features for Efficient Image Super-Resolution","created":"2021-01-21","cited_by_count":8,"area":null},{"id":"2205.08119","title":"ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks","created":"2022-05-17","cited_by_count":8,"area":null},{"id":"2103.11083","title":"Compacting Deep Neural Networks for Internet of Things: Methods and Applications","created":"2021-03-20","cited_by_count":6,"area":null},{"id":"2204.01209","title":"EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection","created":"2022-04-04","cited_by_count":6,"area":null},{"id":"2209.01404","title":"Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies","created":"2022-09-03","cited_by_count":6,"area":null},{"id":"2210.08164","title":"Linear Video Transformer with Feature Fixation","created":"2022-10-15","cited_by_count":6,"area":null},{"id":"2307.16140","title":"Fully $1\\times1$ Convolutional Network for Lightweight Image Super-Resolution","created":"2023-07-30","cited_by_count":6,"area":null},{"id":"2403.07310","title":"How does promoting the minority fraction affect generalization? A theoretical study of the one-hidden-layer neural network on group imbalance","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2503.23472","title":"Efficient Dynamic Attention 3D Convolution for Hyperspectral Image Classification","created":"2025-03-30","cited_by_count":6,"area":null},{"id":"2202.02777","title":"Learning Features with Parameter-Free Layers","created":"2022-02-06","cited_by_count":5,"area":null},{"id":"2204.00452","title":"Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognition","created":"2022-04-01","cited_by_count":5,"area":null},{"id":"2210.13361","title":"NASA: Neural Architecture Search and Acceleration for Hardware Inspired Hybrid Networks","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2409.11786","title":"Efficient Low-Resolution Face Recognition via Bridge Distillation","created":"2024-09-18","cited_by_count":5,"area":null},{"id":"2504.19646","title":"xEdgeFace: Efficient Cross-Spectral Face Recognition for Edge Devices","created":"2025-04-28","cited_by_count":5,"area":null},{"id":"2505.04165","title":"TS-SNN: Temporal Shift Module for Spiking Neural Networks","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2512.02965","title":"UltraFast-LiNET: Light-weight multi-scale shift convolutional network for real-time low-light image enhancement","created":"2025-12-02","cited_by_count":5,"area":null},{"id":"2110.12130","title":"RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection","created":"2021-10-23","cited_by_count":4,"area":null},{"id":"2202.07308","title":"HAA4D: Few-Shot Human Atomic Action Recognition via 3D Spatio-Temporal Skeletal Alignment","created":"2022-02-15","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":"2305.11403","title":"Efficient Mixed Transformer for Single Image Super-Resolution","created":"2023-05-19","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":"2108.10629","title":"Improving Generalization of Batch Whitening by Convolutional Unit Optimization","created":"2021-08-24","cited_by_count":3,"area":null},{"id":"2109.09310","title":"Learning Versatile Convolution Filters for Efficient Visual Recognition","created":"2021-09-20","cited_by_count":3,"area":null},{"id":"2307.04816","title":"Q-YOLO: Efficient Inference for Real-time Object Detection","created":"2023-07-01","cited_by_count":3,"area":null},{"id":"2409.02555","title":"Low-Resolution Object Recognition with Cross-Resolution Relational Contrastive Distillation","created":"2024-09-04","cited_by_count":3,"area":null},{"id":"2105.00967","title":"A lightweight deep learning based cloud detection method for Sentinel-2A imagery fusing multi-scale spectral and spatial features","created":"2021-04-29","cited_by_count":2,"area":null},{"id":"2108.13055","title":"Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2212.08815","title":"FSCNN: A Fast Sparse Convolution Neural Network Inference System","created":"2022-12-17","cited_by_count":2,"area":null},{"id":"2304.01805","title":"Exploration of Lightweight Single Image Denoising with Transformers and Truly Fair Training","created":"2023-04-04","cited_by_count":2,"area":null},{"id":"2509.13662","title":"Deep Lookup Network","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2603.00906","title":"ShiftLUT: Spatial Shift Enhanced Look-Up Tables for Efficient Image Restoration","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2101.00745","title":"DSXplore: Optimizing Convolutional Neural Networks via Sliding-Channel Convolutions","created":"2021-01-04","cited_by_count":1,"area":null},{"id":"2105.14202","title":"Universal Adder Neural Networks","created":"2021-05-29","cited_by_count":1,"area":null},{"id":"2111.02399","title":"Learning Pruned Structure and Weights Simultaneously from Scratch: an Attention based Approach","created":"2021-11-01","cited_by_count":1,"area":null},{"id":"2112.02523","title":"STSM: Spatio-Temporal Shift Module for Efficient Action Recognition","created":"2021-12-05","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":"2407.02881","title":"ShiftAddAug: Augment Multiplication-Free Tiny Neural Network with Hybrid Computation","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2503.16760","title":"Rethinking the Role of Spatial Mixing","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2507.16556","title":"Optimization of DNN-based HSI Segmentation FPGA-based SoC for ADS: A Practical Approach","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2605.04769","title":"Lightweight Cross-Spectral Face Recognition via Contrastive Alignment and Distillation","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2102.10435","title":"MHDeep: Mental Health Disorder Detection System based on Body-Area and Deep Neural Networks","created":"2021-02-20","cited_by_count":0,"area":null},{"id":"2104.01303","title":"Tight Compression: Compressing CNN Through Fine-Grained Pruning and Weight Permutation for Efficient Implementation","created":"2021-04-03","cited_by_count":0,"area":null},{"id":"2109.09495","title":"GhostShiftAddNet: More Features from Energy-Efficient Operations","created":"2021-09-20","cited_by_count":0,"area":null},{"id":"2201.06878","title":"Hardware-Efficient Deconvolution-Based GAN for Edge Computing","created":"2022-01-18","cited_by_count":0,"area":null},{"id":"2202.08399","title":"Shift-Memory Network for Temporal Scene Segmentation","created":"2022-02-17","cited_by_count":0,"area":null},{"id":"2212.08613","title":"Atrous Space Bender U-Net (ASBU-Net/LogiNet)","created":"2022-12-16","cited_by_count":0,"area":null},{"id":"2303.15474","title":"A Heterogeneous Parallel Non-von Neumann Architecture System for Accurate and Efficient Machine Learning Molecular Dynamics","created":"2023-03-26","cited_by_count":0,"area":null},{"id":"2304.11706","title":"Deep Convolutional Tables: Deep Learning without Convolutions","created":"2023-04-23","cited_by_count":0,"area":null},{"id":"2306.13474","title":"Efficient Online Processing with Deep Neural Networks","created":"2023-06-23","cited_by_count":0,"area":null},{"id":"2308.08142","title":"S2R: Exploring a Double-Win Transformer-Based Framework for Ideal and Blind Super-Resolution","created":"2023-08-16","cited_by_count":0,"area":null},{"id":"2310.10166","title":"The Road to On-board Change Detection: A Lightweight Patch-Level Change Detection Network via Exploring the Potential of Pruning and Pooling","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2401.00241","title":"Image Super-Resolution Reconstruction Network based on Enhanced Swin Transformer via Alternating Aggregation of Local-Global Features","created":"2023-12-30","cited_by_count":0,"area":null},{"id":"2402.07200","title":"Outlier-Aware Training for Low-Bit Quantization of Structural Re-Parameterized Networks","created":"2024-02-11","cited_by_count":0,"area":null},{"id":"2402.18007","title":"Mixer is more than just a model","created":"2024-02-28","cited_by_count":0,"area":null},{"id":"2511.00335","title":"Beyond ImageNet: Understanding Cross-Dataset Robustness of Lightweight Vision Models","created":"2025-11-01","cited_by_count":0,"area":null},{"id":"2512.06440","title":"Neural expressiveness for beyond importance model compression","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2512.12847","title":"HaShiFlex: A High-Throughput Hardened Shifter DNN Accelerator with Fine-Tuning Flexibility","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2608.00754","title":"CN101 - A Digital Thermodynamic Computer for Generative AI","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.33077","title":"Parameter-Efficient 3D Segmentation of Liver and Liver tumors: Depthwise factorization Scales Better Than Dense Convolution with Spatial Dimensionality","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}