{"total":147,"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":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241,"area":null},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203,"area":null},{"id":"2103.04505","title":"Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges","created":"2021-03-08","cited_by_count":115,"area":"inference"},{"id":"2404.10518","title":"MobileNetV4 -- Universal Models for the Mobile Ecosystem","created":"2024-04-16","cited_by_count":99,"area":null},{"id":"2104.11892","title":"A Survey of Modern Deep Learning based Object Detection Models","created":"2021-04-24","cited_by_count":98,"area":null},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2106.05022","title":"Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions","created":"2021-06-09","cited_by_count":75,"area":"inference"},{"id":"2201.00814","title":"Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space","created":"2022-01-03","cited_by_count":66,"area":null},{"id":"2101.09336","title":"A Comprehensive Survey on Hardware-Aware Neural Architecture Search","created":"2021-01-22","cited_by_count":61,"area":null},{"id":"2407.00945","title":"Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs","created":"2024-07-01","cited_by_count":53,"area":"moe"},{"id":"2110.11027","title":"FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusion","created":"2021-10-21","cited_by_count":49,"area":null},{"id":"2203.10681","title":"Online Continual Learning for Embedded Devices","created":"2022-03-21","cited_by_count":49,"area":null},{"id":"2101.08940","title":"Hessian-Aware Pruning and Optimal Neural Implant","created":"2021-01-22","cited_by_count":45,"area":null},{"id":"2210.06659","title":"Structural Pruning via Latency-Saliency Knapsack","created":"2022-10-13","cited_by_count":41,"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":"2203.15794","title":"CHEX: CHannel EXploration for CNN Model Compression","created":"2022-03-29","cited_by_count":36,"area":null},{"id":"2106.02022","title":"Single Image Depth Prediction with Wavelet Decomposition","created":"2021-06-03","cited_by_count":34,"area":null},{"id":"2101.10861","title":"A Review on Deep Learning in UAV Remote Sensing","created":"2021-01-22","cited_by_count":32,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2102.03214","title":"Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning","created":"2021-02-05","cited_by_count":30,"area":null},{"id":"2108.13041","title":"Auto-Split: A General Framework of Collaborative Edge-Cloud AI","created":"2021-08-30","cited_by_count":30,"area":null},{"id":"2109.02220","title":"GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization","created":"2021-09-06","cited_by_count":29,"area":null},{"id":"2104.11883","title":"Carrying out CNN Channel Pruning in a White Box","created":"2021-04-24","cited_by_count":22,"area":null},{"id":"2207.12577","title":"Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution","created":"2022-07-25","cited_by_count":20,"area":null},{"id":"2303.07129","title":"AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments","created":"2023-03-13","cited_by_count":19,"area":null},{"id":"2105.03596","title":"Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms","created":"2021-05-08","cited_by_count":18,"area":null},{"id":"2102.10301","title":"Towards Accurate and Compact Architectures via Neural Architecture Transformer","created":"2021-02-20","cited_by_count":17,"area":null},{"id":"2108.08532","title":"An Information Theory-inspired Strategy for Automatic Network Pruning","created":"2021-08-19","cited_by_count":17,"area":null},{"id":"2306.14306","title":"Adaptive Sharpness-Aware Pruning for Robust Sparse Networks","created":"2023-06-25","cited_by_count":17,"area":null},{"id":"2202.07190","title":"Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters","created":"2022-02-15","cited_by_count":16,"area":null},{"id":"2204.11797","title":"PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution","created":"2022-04-25","cited_by_count":16,"area":null},{"id":"2205.01271","title":"Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation","created":"2022-05-03","cited_by_count":16,"area":null},{"id":"2104.11939","title":"Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation","created":"2021-04-24","cited_by_count":14,"area":null},{"id":"2203.04206","title":"Lightweight Monocular Depth Estimation through Guided Decoding","created":"2022-03-08","cited_by_count":14,"area":null},{"id":"2103.15750","title":"Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design","created":"2021-03-25","cited_by_count":13,"area":null},{"id":"2104.00031","title":"NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimization","created":"2021-03-31","cited_by_count":13,"area":null},{"id":"2112.09245","title":"Automated Deep Learning: Neural Architecture Search Is Not the End","created":"2021-12-16","cited_by_count":13,"area":null},{"id":"2102.08619","title":"Rethinking Co-design of Neural Architectures and Hardware Accelerators","created":"2021-02-17","cited_by_count":12,"area":null},{"id":"2105.12053","title":"Real-time Monocular Depth Estimation with Sparse Supervision on Mobile","created":"2021-05-25","cited_by_count":12,"area":null},{"id":"2211.02206","title":"Soft Masking for Cost-Constrained Channel Pruning","created":"2022-11-04","cited_by_count":12,"area":null},{"id":"2107.10624","title":"LANA: Latency Aware Network Acceleration","created":"2021-07-12","cited_by_count":11,"area":"distill"},{"id":"2312.15322","title":"Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization","created":"2023-12-23","cited_by_count":10,"area":null},{"id":"2103.13253","title":"Learning Versatile Neural Architectures by Propagating Network Codes","created":"2021-03-24","cited_by_count":9,"area":null},{"id":"2109.00642","title":"Searching for Efficient Multi-Stage Vision Transformers","created":"2021-09-01","cited_by_count":9,"area":null},{"id":"2112.15131","title":"Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2306.05857","title":"How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective","created":"2023-06-09","cited_by_count":9,"area":null},{"id":"2405.19816","title":"Growing Tiny Networks: Spotting Expressivity Bottlenecks and Fixing Them Optimally","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2102.06599","title":"Neural Architecture Search as Program Transformation Exploration","created":"2021-02-12","cited_by_count":8,"area":null},{"id":"2110.10811","title":"HALP: Hardware-Aware Latency Pruning","created":"2021-10-20","cited_by_count":8,"area":null},{"id":"2111.01203","title":"One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search","created":"2021-11-01","cited_by_count":8,"area":null},{"id":"2201.07677","title":"Tiny, always-on and fragile: Bias propagation through design choices in on-device machine learning workflows","created":"2022-01-19","cited_by_count":8,"area":null},{"id":"2209.10507","title":"Gemino: Practical and Robust Neural Compression for Video Conferencing","created":"2022-09-21","cited_by_count":8,"area":null},{"id":"2106.04723","title":"OODIn: An Optimised On-Device Inference Framework for Heterogeneous Mobile Devices","created":"2021-06-08","cited_by_count":7,"area":null},{"id":"2108.11105","title":"Lightweight Monocular Depth with a Novel Neural Architecture Search Method","created":"2021-08-25","cited_by_count":7,"area":null},{"id":"2109.08880","title":"Computational Imaging and Artificial Intelligence: The Next Revolution of Mobile Vision","created":"2021-09-18","cited_by_count":7,"area":null},{"id":"2111.11581","title":"Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration","created":"2021-11-22","cited_by_count":7,"area":null},{"id":"2105.11694","title":"FNAS: Uncertainty-Aware Fast Neural Architecture Search","created":"2021-05-25","cited_by_count":6,"area":null},{"id":"2109.10060","title":"DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers","created":"2021-09-21","cited_by_count":6,"area":null},{"id":"2111.06660","title":"Frequency learning for structured CNN filters with Gaussian fractional derivatives","created":"2021-11-12","cited_by_count":6,"area":null},{"id":"2105.03608","title":"Optimising Resource Management for Embedded Machine Learning","created":"2021-05-08","cited_by_count":5,"area":null},{"id":"2107.06916","title":"Training Compact CNNs for Image Classification using Dynamic-coded Filter Fusion","created":"2021-07-14","cited_by_count":5,"area":null},{"id":"2202.05397","title":"Neural Architecture Search for Energy Efficient Always-on Audio Models","created":"2022-02-09","cited_by_count":5,"area":null},{"id":"2504.02168","title":"MDP: Multidimensional Vision Model Pruning with Latency Constraint","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2101.05363","title":"NetCut: Real-Time DNN Inference Using Layer Removal","created":"2021-01-13","cited_by_count":4,"area":null},{"id":"2102.05956","title":"The Benefit of the Doubt: Uncertainty Aware Sensing for Edge Computing Platforms","created":"2021-02-11","cited_by_count":4,"area":null},{"id":"2107.08199","title":"Dynamic Transformer for Efficient Machine Translation on Embedded Devices","created":"2021-07-17","cited_by_count":4,"area":null},{"id":"2108.10506","title":"Real-Time Monocular Human Depth Estimation and Segmentation on Embedded Systems","created":"2021-08-24","cited_by_count":4,"area":null},{"id":"2212.07818","title":"Towards Hardware-Specific Automatic Compression of Neural Networks","created":"2022-12-15","cited_by_count":4,"area":null},{"id":"2301.10999","title":"PerfSAGE: Generalized Inference Performance Predictor for Arbitrary Deep Learning Models on Edge Devices","created":"2023-01-26","cited_by_count":4,"area":null},{"id":"2302.08571","title":"A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques","created":"2023-02-16","cited_by_count":4,"area":null},{"id":"2406.12079","title":"Multi-Dimensional Pruning: Joint Channel, Layer and Block Pruning with Latency Constraint","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2305.07135","title":"Divide-and-Conquer the NAS puzzle in Resource Constrained Federated Learning Systems","created":"2023-05-11","cited_by_count":3,"area":null},{"id":"2308.04672","title":"Resource Constrained Model Compression via Minimax Optimization for Spiking Neural Networks","created":"2023-08-09","cited_by_count":3,"area":null},{"id":"2101.02663","title":"L2PF -- Learning to Prune Faster","created":"2021-01-07","cited_by_count":2,"area":null},{"id":"2103.12496","title":"Revisiting Self-Supervised Monocular Depth Estimation","created":"2021-03-23","cited_by_count":2,"area":null},{"id":"2105.03600","title":"Incremental Training and Group Convolution Pruning for Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms","created":"2021-05-08","cited_by_count":2,"area":null},{"id":"2106.12958","title":"Self-Supervised Monocular Depth Estimation of Untextured Indoor Rotated Scenes","created":"2021-06-24","cited_by_count":2,"area":null},{"id":"2106.14465","title":"Exploring convolutional neural networks with transfer learning for diagnosing Lyme disease from skin lesion images","created":"2021-06-28","cited_by_count":2,"area":null},{"id":"2106.15021","title":"How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architectures","created":"2021-06-21","cited_by_count":2,"area":null},{"id":"2109.04925","title":"Rapid Model Architecture Adaption for Meta-Learning","created":"2021-09-10","cited_by_count":2,"area":null},{"id":"2203.12412","title":"U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search","created":"2022-03-23","cited_by_count":2,"area":null},{"id":"2207.01260","title":"CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2306.05682","title":"Lightweight Monocular Depth Estimation via Token-Sharing Transformer","created":"2023-06-09","cited_by_count":2,"area":null},{"id":"2409.07925","title":"A framework for measuring the training efficiency of a neural architecture","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2607.06922","title":"Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2104.09191","title":"Compact CNN Structure Learning by Knowledge Distillation","created":"2021-04-19","cited_by_count":1,"area":"distill"},{"id":"2105.03176","title":"ANNETTE: Accurate Neural Network Execution Time Estimation with Stacked Models","created":"2021-05-07","cited_by_count":1,"area":null},{"id":"2106.05345","title":"Cocktail: Leveraging Ensemble Learning for Optimized Model Serving in Public Cloud","created":"2021-06-09","cited_by_count":1,"area":null},{"id":"2109.05432","title":"Prioritized Subnet Sampling for Resource-Adaptive Supernet Training","created":"2021-09-12","cited_by_count":1,"area":null},{"id":"2202.12417","title":"Optimal channel selection with discrete QCQP","created":"2022-02-24","cited_by_count":1,"area":null},{"id":"2203.13921","title":"A Semi-Decoupled Approach to Fast and Optimal Hardware-Software Co-Design of Neural Accelerators","created":"2022-03-25","cited_by_count":1,"area":null},{"id":"2204.04416","title":"E^2TAD: An Energy-Efficient Tracking-based Action Detector","created":"2022-04-09","cited_by_count":1,"area":null},{"id":"2208.10498","title":"Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey","created":"2022-08-22","cited_by_count":1,"area":null},{"id":"2210.02620","title":"Inference Latency Prediction at the Edge","created":"2022-10-06","cited_by_count":1,"area":null},{"id":"2211.10963","title":"A Lightweight Domain Adaptive Absolute Pose Regressor Using Barlow Twins Objective","created":"2022-11-20","cited_by_count":1,"area":null},{"id":"2212.02687","title":"Vision Transformer Computation and Resilience for Dynamic Inference","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2304.06393","title":"Learning Accurate Performance Predictors for Ultrafast Automated Model Compression","created":"2023-04-13","cited_by_count":1,"area":null},{"id":"2305.14403","title":"Layer-adaptive Structured Pruning Guided by Latency","created":"2023-05-23","cited_by_count":1,"area":null}],"next_cursor":"100"}