{"list":"other","total":103,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"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":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"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":"2106.08265","title":"Towards Total Recall in Industrial Anomaly Detection","created":"2021-06-15","cited_by_count":776},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"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":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"id":"1907.09682","title":"Similarity-Preserving Knowledge Distillation","created":"2019-07-23","cited_by_count":516},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"1805.06085","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","created":"2018-05-16","cited_by_count":467},{"id":"1811.08886","title":"HAQ: Hardware-Aware Automated Quantization with Mixed Precision","created":"2018-11-21","cited_by_count":443},{"id":"1310.1531","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","created":"2013-10-06","cited_by_count":424},{"id":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1403.6382","title":"CNN Features off-the-shelf: an Astounding Baseline for Recognition","created":"2014-03-23","cited_by_count":316},{"id":"2004.05937","title":"Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks","created":"2020-04-13","cited_by_count":316},{"id":"1511.06523","title":"WIDER FACE: A Face Detection Benchmark","created":"2015-11-20","cited_by_count":298},{"id":"2007.10319","title":"MCUNet: Tiny Deep Learning on IoT Devices","created":"2020-07-20","cited_by_count":273},{"id":"2106.05237","title":"Knowledge distillation: A good teacher is patient and consistent","created":"2021-06-09","cited_by_count":259},{"id":"1903.10258","title":"MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning","created":"2019-03-25","cited_by_count":227},{"id":"1612.01064","title":"Trained Ternary Quantization","created":"2016-12-04","cited_by_count":208},{"id":"1412.6553","title":"Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition","created":"2014-12-19","cited_by_count":203},{"id":"1412.6115","title":"Compressing Deep Convolutional Networks using Vector Quantization","created":"2014-12-18","cited_by_count":195},{"id":"1512.01274","title":"MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems","created":"2015-12-03","cited_by_count":195},{"id":"1806.06193","title":"Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning","created":"2018-06-16","cited_by_count":174},{"id":"2010.08678","title":"TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems","created":"2020-10-17","cited_by_count":165},{"id":"1812.08011","title":"Training Deep Neural Networks with 8-bit Floating Point Numbers","created":"2018-12-19","cited_by_count":164},{"id":"1511.06530","title":"Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications","created":"2015-11-20","cited_by_count":162},{"id":"2206.15472","title":"On-Device Training Under 256KB Memory","created":"2022-06-30","cited_by_count":160},{"id":"1708.05237","title":"S$^3$FD: Single Shot Scale-invariant Face Detector","created":"2017-08-17","cited_by_count":142},{"id":"2111.11837","title":"Focal and Global Knowledge Distillation for Detectors","created":"2021-11-23","cited_by_count":142},{"id":"1805.08166","title":"Learning to Optimize Tensor Programs","created":"2018-05-21","cited_by_count":140},{"id":"1405.3531","title":"Return of the Devil in the Details: Delving Deep into Convolutional Nets","created":"2014-05-14","cited_by_count":122},{"id":"1801.06601","title":"CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs","created":"2018-01-19","cited_by_count":121},{"id":"1605.07678","title":"An Analysis of Deep Neural Network Models for Practical Applications","created":"2016-05-24","cited_by_count":116},{"id":"2003.00152","title":"Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs","created":"2020-02-29","cited_by_count":104},{"id":"2110.15352","title":"MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning","created":"2021-10-28","cited_by_count":89},{"id":"1606.03401","title":"Memory-Efficient Backpropagation Through Time","created":"2016-06-10","cited_by_count":78},{"id":"1909.09145","title":"Detailed comparison of communication efficiency of split learning and federated learning","created":"2019-09-18","cited_by_count":77},{"id":"2002.12418","title":"MNN: A Universal and Efficient Inference Engine","created":"2020-02-27","cited_by_count":65},{"id":"2103.08295","title":"TinyOL: TinyML with Online-Learning on Microcontrollers","created":"2021-03-15","cited_by_count":65},{"id":"2008.07127","title":"DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUs","created":"2020-08-17","cited_by_count":58},{"id":"2010.14246","title":"$\\mu$NAS: Constrained Neural Architecture Search for Microcontrollers","created":"2020-10-27","cited_by_count":55},{"id":"1612.07771","title":"Highway and Residual Networks learn Unrolled Iterative Estimation","created":"2016-12-22","cited_by_count":52},{"id":"1905.12107","title":"SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers","created":"2019-05-28","cited_by_count":52},{"id":"1910.13349","title":"E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings","created":"2019-10-29","cited_by_count":36},{"id":"1810.10703","title":"K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning","created":"2018-10-25","cited_by_count":34},{"id":"1905.13082","title":"Memory-Driven Mixed Low Precision Quantization For Enabling Deep Network Inference On Microcontrollers","created":"2019-05-30","cited_by_count":33},{"id":"2007.11622","title":"TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning","created":"2020-07-22","cited_by_count":32},{"id":"2206.07509","title":"Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading","created":"2022-06-15","cited_by_count":29},{"id":"2003.02369","title":"Ordering Chaos: Memory-Aware Scheduling of Irregularly Wired Neural Networks for Edge Devices","created":"2020-03-04","cited_by_count":27},{"id":"2104.01454","title":"Few-Shot Keyword Spotting in Any Language","created":"2021-04-03","cited_by_count":27},{"id":"2207.07697","title":"POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging","created":"2022-07-15","cited_by_count":26},{"id":"1904.10633","title":"LFFD: A Light and Fast Face Detector for Edge Devices","created":"2019-04-24","cited_by_count":21},{"id":"2002.11921","title":"RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference","created":"2020-02-27","cited_by_count":21},{"id":"1810.00859","title":"Dynamic Sparse Graph for Efficient Deep Learning","created":"2018-10-01","cited_by_count":18},{"id":"1906.06579","title":"EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse","created":"2019-06-15","cited_by_count":18},{"id":"2008.04245","title":"TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices","created":"2020-08-10","cited_by_count":16},{"id":"1910.05110","title":"Neural networks on microcontrollers: saving memory at inference via operator reordering","created":"2019-10-02","cited_by_count":15},{"id":"1902.01492","title":"Optimally Scheduling CNN Convolutions for Efficient Memory Access","created":"2019-02-04","cited_by_count":10},{"id":"2007.00302","title":"Robustifying the Deployment of tinyML Models for Autonomous mini-vehicles","created":"2020-07-01","cited_by_count":10},{"id":"2009.14385","title":"AttendNets: Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers","created":"2020-09-30","cited_by_count":10},{"id":"2011.14858","title":"A Tiny CNN Architecture for Medical Face Mask Detection for Resource-Constrained Endpoints","created":"2020-11-30","cited_by_count":10},{"id":"2201.05842","title":"UDC: Unified DNAS for Compressible TinyML Models","created":"2022-01-15","cited_by_count":10},{"id":"2101.08744","title":"Enabling Large Neural Networks on Tiny Microcontrollers with Swapping","created":"2021-01-14","cited_by_count":9},{"id":"2103.05267","title":"Memory-Efficient, Limb Position-Aware Hand Gesture Recognition using Hyperdimensional Computing","created":"2021-03-09","cited_by_count":8}],"next_cursor":"100"}