{"list":"other","total":94,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"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":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"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":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"1710.03463","title":"Learning to Generalize: Meta-Learning for Domain Generalization","created":"2017-10-10","cited_by_count":763},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"1806.08342","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","created":"2018-06-21","cited_by_count":521},{"id":"1903.02891","title":"Robust and Communication-Efficient Federated Learning from Non-IID Data","created":"2019-03-07","cited_by_count":419},{"id":"2001.00326","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","created":"2020-01-02","cited_by_count":416},{"id":"1804.05271","title":"Adaptive Federated Learning in Resource Constrained Edge Computing Systems","created":"2018-04-14","cited_by_count":409},{"id":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"id":"2004.12993","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","created":"2020-04-27","cited_by_count":332},{"id":"2007.08489","title":"Do Adversarially Robust ImageNet Models Transfer Better?","created":"2020-07-16","cited_by_count":316},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"2007.10319","title":"MCUNet: Tiny Deep Learning on IoT Devices","created":"2020-07-20","cited_by_count":273},{"id":"2006.02903","title":"A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions","created":"2020-06-01","cited_by_count":254},{"id":"2111.15668","title":"AdaViT: Adaptive Vision Transformers for Efficient Image Recognition","created":"2021-11-30","cited_by_count":228},{"id":"2006.07500","title":"Domain Generalization using Causal Matching","created":"2020-06-12","cited_by_count":225},{"id":"1805.11783","title":"To Trust Or Not To Trust A Classifier","created":"2018-05-30","cited_by_count":207},{"id":"2210.11466","title":"Surgical Fine-Tuning Improves Adaptation to Distribution Shifts","created":"2022-10-20","cited_by_count":205},{"id":"1812.11494","title":"Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)","created":"2018-12-30","cited_by_count":191},{"id":"1711.08393","title":"BlockDrop: Dynamic Inference Paths in Residual Networks","created":"2017-11-22","cited_by_count":189},{"id":"1911.02417","title":"Energy Efficient Federated Learning Over Wireless Communication Networks","created":"2019-11-06","cited_by_count":181},{"id":"2110.11328","title":"A Fine-Grained Analysis on Distribution Shift","created":"2021-10-21","cited_by_count":171},{"id":"1811.08737","title":"SpotTune: Transfer Learning through Adaptive Fine-tuning","created":"2018-11-21","cited_by_count":168},{"id":"2007.07400","title":"Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics","created":"2020-07-14","cited_by_count":161},{"id":"2206.15472","title":"On-Device Training Under 256KB Memory","created":"2022-06-30","cited_by_count":160},{"id":"2008.10937","title":"A Survey on Evolutionary Neural Architecture Search","created":"2020-08-25","cited_by_count":142},{"id":"1611.05128","title":"Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning","created":"2016-11-16","cited_by_count":134},{"id":"1810.05331","title":"Dynamic Channel Pruning: Feature Boosting and Suppression","created":"2018-10-12","cited_by_count":129},{"id":"1612.02297","title":"Spatially Adaptive Computation Time for Residual Networks","created":"2016-12-07","cited_by_count":118},{"id":"2007.07645","title":"Learning to Learn with Variational Information Bottleneck for Domain Generalization","created":"2020-07-15","cited_by_count":102},{"id":"1903.07424","title":"Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregation","created":"2019-03-18","cited_by_count":100},{"id":"1911.03090","title":"What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning","created":"2019-11-08","cited_by_count":89},{"id":"2103.10584","title":"HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark","created":"2021-03-19","cited_by_count":84},{"id":"2001.04756","title":"Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approach","created":"2020-01-14","cited_by_count":81},{"id":"1801.08618","title":"JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services","created":"2018-01-25","cited_by_count":80},{"id":"1812.08934","title":"ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation","created":"2018-12-21","cited_by_count":76},{"id":"2106.05022","title":"Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions","created":"2021-06-09","cited_by_count":75},{"id":"2106.15831","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","created":"2021-06-30","cited_by_count":75},{"id":"2312.04916","title":"EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism","created":"2023-12-08","cited_by_count":69},{"id":"1509.08971","title":"Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognition","created":"2015-09-29","cited_by_count":67},{"id":"2001.10422","title":"NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search","created":"2020-01-28","cited_by_count":64},{"id":"2108.01621","title":"Domain Generalization via Gradient Surgery","created":"2021-08-03","cited_by_count":60},{"id":"1910.02366","title":"Splitting Steepest Descent for Growing Neural Architectures","created":"2019-10-06","cited_by_count":55},{"id":"2010.14246","title":"$\\mu$NAS: Constrained Neural Architecture Search for Microcontrollers","created":"2020-10-27","cited_by_count":55},{"id":"2012.04550","title":"In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness","created":"2020-12-08","cited_by_count":50},{"id":"2102.01386","title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning","created":"2021-02-02","cited_by_count":48},{"id":"1904.09546","title":"DeepCaps: Going Deeper with Capsule Networks","created":"2019-04-21","cited_by_count":42},{"id":"1907.06040","title":"Energy-Efficient Radio Resource Allocation for Federated Edge Learning","created":"2019-07-13","cited_by_count":39},{"id":"2106.05409","title":"Zero Time Waste: Recycling Predictions in Early Exit Neural Networks","created":"2021-06-09","cited_by_count":39},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32},{"id":"2008.03997","title":"HAPI: Hardware-Aware Progressive Inference","created":"2020-08-10","cited_by_count":30},{"id":"1810.07751","title":"Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems","created":"2018-09-28","cited_by_count":25},{"id":"2206.04685","title":"Predictive Exit: Prediction of Fine-Grained Early Exits for Computation- and Energy-Efficient Inference","created":"2022-06-09","cited_by_count":24},{"id":"1911.00188","title":"Energy-Aware Analog Aggregation for Federated Learning with Redundant Data","created":"2019-11-01","cited_by_count":23},{"id":"1607.05418","title":"Runtime Configurable Deep Neural Networks for Energy-Accuracy Trade-off","created":"2016-07-19","cited_by_count":19},{"id":"1910.03103","title":"Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent","created":"2019-10-07","cited_by_count":18},{"id":"2102.01393","title":"It's always personal: Using Early Exits for Efficient On-Device CNN Personalisation","created":"2021-02-02","cited_by_count":18},{"id":"2310.18329","title":"Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices","created":"2023-10-19","cited_by_count":17},{"id":"1703.09844","title":"Multi-Scale Dense Networks for Resource Efficient Image Classification","created":"2017-03-29","cited_by_count":16},{"id":"2008.08476","title":"NASCaps: A Framework for Neural Architecture Search to Optimize the Accuracy and Hardware Efficiency of Convolutional Capsule Networks","created":"2020-08-19","cited_by_count":16},{"id":"2101.04866","title":"Towards Energy Efficient Federated Learning over 5G+ Mobile Devices","created":"2021-01-13","cited_by_count":16},{"id":"1702.07780","title":"Changing Model Behavior at Test-Time Using Reinforcement Learning","created":"2017-02-24","cited_by_count":15},{"id":"2207.09455","title":"To update or not to update? Neurons at equilibrium in deep models","created":"2022-07-19","cited_by_count":13},{"id":"2311.11420","title":"LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms","created":"2023-11-19","cited_by_count":11},{"id":"2202.08174","title":"Towards Battery-Free Machine Learning and Inference in Underwater Environments","created":"2022-02-16","cited_by_count":9},{"id":"2310.07361","title":"Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters","created":"2023-10-11","cited_by_count":9},{"id":"2008.11995","title":"A Flexible Selection Scheme for Minimum-Effort Transfer Learning","created":"2020-08-27","cited_by_count":8},{"id":"1810.07052","title":"Shallow-Deep Networks: Understanding and Mitigating Network Overthinking","created":"2018-10-16","cited_by_count":7},{"id":"2103.10858","title":"Toward Compact Deep Neural Networks via Energy-Aware Pruning","created":"2021-03-19","cited_by_count":6},{"id":"2312.05282","title":"Towards On-device Learning on the Edge: Ways to Select Neurons to Update under a Budget Constraint","created":"2023-12-08","cited_by_count":6},{"id":"1805.10982","title":"Dynamically Sacrificing Accuracy for Reduced Computation: Cascaded Inference Based on Softmax Confidence","created":"2018-05-28","cited_by_count":5},{"id":"1909.01968","title":"ACES -- Automatic Configuration of Energy Harvesting Sensors with Reinforcement Learning","created":"2019-09-04","cited_by_count":5},{"id":"2102.11274","title":"Sustainable Federated Learning","created":"2021-02-22","cited_by_count":5},{"id":"2306.08951","title":"MLonMCU: TinyML Benchmarking with Fast Retargeting","created":"2023-06-15","cited_by_count":5},{"id":"2204.03431","title":"Energy-Efficient Adaptive Machine Learning on IoT End-Nodes With Class-Dependent Confidence","created":"2022-04-07","cited_by_count":3},{"id":"2304.04164","title":"Gradient Sparsification for Efficient Wireless Federated Learning with Differential Privacy","created":"2023-04-09","cited_by_count":3},{"id":"2311.09690","title":"CDMPP: A Device-Model Agnostic Framework for Latency Prediction of Tensor Programs","created":"2023-11-16","cited_by_count":3},{"id":"2110.07542","title":"ALFRED: Virtual Memory for Intermittent Computing","created":"2021-10-14","cited_by_count":1},{"id":"2302.06478","title":"Divide and Save: Splitting Workload Among Containers in an Edge Device to Save Energy and Time","created":"2023-02-13","cited_by_count":1},{"id":"2402.05319","title":"Optimal energy-aware task scheduling for batteryless IoT devices","created":"2024-02-07","cited_by_count":1}],"next_cursor":null}