{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"1606.06160","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","created":"2016-06-20","cited_by_count":569},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"1707.06342","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","created":"2017-07-20","cited_by_count":442},{"id":"1602.01528","title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","created":"2016-02-04","cited_by_count":295},{"id":"1812.09926","title":"SNAS: Stochastic Neural Architecture Search","created":"2018-12-24","cited_by_count":289},{"id":"1408.5093","title":"Caffe: Convolutional Architecture for Fast Feature Embedding","created":"2014-06-20","cited_by_count":288},{"id":"1611.02167","title":"Designing Neural Network Architectures using Reinforcement Learning","created":"2016-11-07","cited_by_count":279},{"id":"2007.10319","title":"MCUNet: Tiny Deep Learning on IoT Devices","created":"2020-07-20","cited_by_count":273},{"id":"1902.07638","title":"Random Search and Reproducibility for Neural Architecture Search","created":"2019-02-20","cited_by_count":254},{"id":"2006.04647","title":"Neural Architecture Search without Training","created":"2020-06-08","cited_by_count":244},{"id":"1702.03044","title":"Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights","created":"2017-02-10","cited_by_count":217},{"id":"1612.01064","title":"Trained Ternary Quantization","created":"2016-12-04","cited_by_count":208},{"id":"1605.04711","title":"Ternary Weight Networks","created":"2016-05-16","cited_by_count":204},{"id":"2101.08134","title":"Zero-Cost Proxies for Lightweight NAS","created":"2021-01-20","cited_by_count":199},{"id":"1808.07233","title":"Neural Architecture Optimization","created":"2018-08-22","cited_by_count":167},{"id":"1808.00362","title":"Deep Appearance Models for Face Rendering","created":"2018-08-01","cited_by_count":164},{"id":"1612.07119","title":"FINN: A Framework for Fast, Scalable Binarized Neural Network Inference","created":"2016-12-01","cited_by_count":150},{"id":"1905.11116","title":"Finding Task-Relevant Features for Few-Shot Learning by Category Traversal","created":"2019-05-27","cited_by_count":101},{"id":"2001.00138","title":"PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning","created":"2020-01-01","cited_by_count":76},{"id":"1707.09870","title":"Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM","created":"2017-07-24","cited_by_count":61},{"id":"2101.09336","title":"A Comprehensive Survey on Hardware-Aware Neural Architecture Search","created":"2021-01-22","cited_by_count":61},{"id":"1711.02017","title":"NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm","created":"2017-11-06","cited_by_count":60},{"id":"1907.04650","title":"Hardware/Software Co-Exploration of Neural Architectures","created":"2019-07-06","cited_by_count":50},{"id":"1909.05073","title":"PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices","created":"2019-09-06","cited_by_count":50},{"id":"2006.06863","title":"Few-shot Neural Architecture Search","created":"2020-06-11","cited_by_count":50},{"id":"1510.03009","title":"Neural Networks with Few Multiplications","created":"2015-10-11","cited_by_count":48},{"id":"1904.04421","title":"FPGA/DNN Co-Design: An Efficient Design Methodology for IoT Intelligence on the Edge","created":"2019-04-09","cited_by_count":48},{"id":"2002.04116","title":"Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks","created":"2020-02-10","cited_by_count":43},{"id":"1812.11677","title":"ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of Multipliers","created":"2018-12-31","cited_by_count":42},{"id":"1901.11211","title":"Accuracy vs. Efficiency: Achieving Both through FPGA-Implementation Aware Neural Architecture Search","created":"2019-01-31","cited_by_count":38},{"id":"2005.02563","title":"EDD: Efficient Differentiable DNN Architecture and Implementation Co-search for Embedded AI Solutions","created":"2020-05-06","cited_by_count":36},{"id":"1908.11263","title":"PULP-NN: Accelerating Quantized Neural Networks on Parallel Ultra-Low-Power RISC-V Processors","created":"2019-08-29","cited_by_count":35},{"id":"1909.09709","title":"SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems","created":"2019-09-20","cited_by_count":27},{"id":"2107.11673","title":"ScaleHLS: A New Scalable High-Level Synthesis Framework on Multi-Level Intermediate Representation","created":"2021-07-24","cited_by_count":21},{"id":"1809.00110","title":"DAC-SDC Low Power Object Detection Challenge for UAV Applications","created":"2018-09-01","cited_by_count":18},{"id":"1811.08634","title":"Synetgy: Algorithm-hardware Co-design for ConvNet Accelerators on Embedded FPGAs","created":"2018-11-21","cited_by_count":18},{"id":"2005.08501","title":"VecQ: Minimal Loss DNN Model Compression With Vectorized Weight Quantization","created":"2020-05-18","cited_by_count":15},{"id":"2108.01899","title":"Generic Neural Architecture Search via Regression","created":"2021-08-04","cited_by_count":14},{"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},{"id":"2205.11656","title":"FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?","created":"2022-05-23","cited_by_count":12},{"id":"2005.11074","title":"An Introduction to Neural Architecture Search for Convolutional Networks","created":"2020-05-22","cited_by_count":10},{"id":"1805.03648","title":"Parallel Programming for FPGAs","created":"2018-05-09","cited_by_count":9},{"id":"1911.07446","title":"NAIS: Neural Architecture and Implementation Search and its Applications in Autonomous Driving","created":"2019-11-18","cited_by_count":9},{"id":"2004.03804","title":"HybridDNN: A Framework for High-Performance Hybrid DNN Accelerator Design and Implementation","created":"2020-04-08","cited_by_count":9},{"id":"1808.04311","title":"Design Flow of Accelerating Hybrid Extremely Low Bit-width Neural Network in Embedded FPGA","created":"2018-07-31","cited_by_count":7},{"id":"1903.01531","title":"Ternary Hybrid Neural-Tree Networks for Highly Constrained IoT Applications","created":"2019-03-04","cited_by_count":4},{"id":"1905.04159","title":"Single-Path NAS: Device-Aware Efficient ConvNet Design","created":"2019-05-10","cited_by_count":4},{"id":"2104.04000","title":"Software/Hardware Co-design for Multi-modal Multi-task Learning in Autonomous Systems","created":"2021-04-08","cited_by_count":4},{"id":"2106.06577","title":"A3C-S: Automated Agent Accelerator Co-Search towards Efficient Deep Reinforcement Learning","created":"2021-06-11","cited_by_count":3}],"next_cursor":null}