{"list":"other","total":73,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"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":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1707.02921","title":"Enhanced Deep Residual Networks for Single Image Super-Resolution","created":"2017-07-10","cited_by_count":1552},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"1703.09039","title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","created":"2017-03-27","cited_by_count":434},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"id":"2111.14887","title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","created":"2021-11-29","cited_by_count":300},{"id":"1807.10029","title":"LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks","created":"2018-07-26","cited_by_count":274},{"id":"1808.00278","title":"Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm","created":"2018-08-01","cited_by_count":235},{"id":"1906.06423","title":"Fixing the train-test resolution discrepancy","created":"2019-06-14","cited_by_count":209},{"id":"1710.09854","title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","created":"2017-10-26","cited_by_count":201},{"id":"2004.03333","title":"Binary Neural Networks: A Survey","created":"2020-03-31","cited_by_count":190},{"id":"2003.03488","title":"ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions","created":"2020-03-07","cited_by_count":184},{"id":"2012.15701","title":"BinaryBERT: Pushing the Limit of BERT Quantization","created":"2020-12-31","cited_by_count":178},{"id":"1909.10788","title":"Forward and Backward Information Retention for Accurate Binary Neural Networks","created":"2019-09-24","cited_by_count":169},{"id":"1611.05128","title":"Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning","created":"2016-11-16","cited_by_count":134},{"id":"1605.07678","title":"An Analysis of Deep Neural Network Models for Practical Applications","created":"2016-05-24","cited_by_count":116},{"id":"2003.11535","title":"Training Binary Neural Networks with Real-to-Binary Convolutions","created":"2020-03-25","cited_by_count":112},{"id":"1912.13200","title":"AdderNet: Do We Really Need Multiplications in Deep Learning?","created":"2019-12-31","cited_by_count":82},{"id":"1810.00736","title":"Benchmark Analysis of Representative Deep Neural Network Architectures","created":"2018-10-01","cited_by_count":77},{"id":"2009.13055","title":"Rotated Binary Neural Network","created":"2020-09-28","cited_by_count":77},{"id":"1706.02379","title":"Training Quantized Nets: A Deeper Understanding","created":"2017-06-07","cited_by_count":75},{"id":"2203.06390","title":"BiBERT: Accurate Fully Binarized BERT","created":"2022-03-12","cited_by_count":73},{"id":"2210.08277","title":"Deep Differentiable Logic Gate Networks","created":"2022-10-15","cited_by_count":67},{"id":"1904.02823","title":"Regularizing Activation Distribution for Training Binarized Deep Networks","created":"2019-04-04","cited_by_count":61},{"id":"1906.02107","title":"Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization","created":"2019-06-05","cited_by_count":60},{"id":"1810.00861","title":"ProxQuant: Quantized Neural Networks via Proximal Operators","created":"2018-10-01","cited_by_count":59},{"id":"1611.01600","title":"Loss-aware Binarization of Deep Networks","created":"2016-11-05","cited_by_count":56},{"id":"2205.13016","title":"BiT: Robustly Binarized Multi-distilled Transformer","created":"2022-05-25","cited_by_count":52},{"id":"2010.14298","title":"A Statistical Framework for Low-bitwidth Training of Deep Neural Networks","created":"2020-10-27","cited_by_count":51},{"id":"2112.00133","title":"PokeBNN: A Binary Pursuit of Lightweight Accuracy","created":"2021-11-30","cited_by_count":49},{"id":"2006.14591","title":"Bidirectional compression in heterogeneous settings for distributed or federated learning with partial participation: tight convergence guarantees","created":"2020-06-25","cited_by_count":46},{"id":"2009.08695","title":"Searching for Low-Bit Weights in Quantized Neural Networks","created":"2020-09-18","cited_by_count":44},{"id":"1509.05753","title":"Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapses","created":"2015-09-18","cited_by_count":39},{"id":"2208.08084","title":"AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets","created":"2022-08-17","cited_by_count":38},{"id":"1811.10413","title":"Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation","created":"2018-11-22","cited_by_count":37},{"id":"1809.04070","title":"Interstellar: Using Halide's Scheduling Language to Analyze DNN Accelerators","created":"2018-09-10","cited_by_count":34},{"id":"2202.05239","title":"F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization","created":"2022-02-10","cited_by_count":28},{"id":"2301.11233","title":"BiBench: Benchmarking and Analyzing Network Binarization","created":"2023-01-26","cited_by_count":22},{"id":"1803.03383","title":"High-Accuracy Low-Precision Training","created":"2018-03-09","cited_by_count":20},{"id":"1807.06964","title":"Bridging the Accuracy Gap for 2-bit Quantized Neural Networks (QNN)","created":"2018-07-17","cited_by_count":19},{"id":"1910.08237","title":"Mirror Descent View for Neural Network Quantization","created":"2019-10-18","cited_by_count":16},{"id":"2211.12933","title":"Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket","created":"2022-11-23","cited_by_count":14},{"id":"2206.09909","title":"Low-Precision Stochastic Gradient Langevin Dynamics","created":"2022-06-20","cited_by_count":12},{"id":"2102.04270","title":"Enabling Binary Neural Network Training on the Edge","created":"2021-02-08","cited_by_count":11},{"id":"2006.08178","title":"Binary DAD-Net: Binarized Driveable Area Detection Network for Autonomous Driving","created":"2020-06-15","cited_by_count":10},{"id":"2204.07439","title":"INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold","created":"2022-04-15","cited_by_count":9},{"id":"1812.04353","title":"Proximal Mean-field for Neural Network Quantization","created":"2018-12-11","cited_by_count":6},{"id":"2209.01404","title":"Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies","created":"2022-09-03","cited_by_count":6},{"id":"1505.05401","title":"A Max-Sum algorithm for training discrete neural networks","created":"2015-05-20","cited_by_count":5},{"id":"2203.04821","title":"Neural Network Training on In-memory-computing Hardware with Radix-4 Gradients","created":"2022-03-09","cited_by_count":4},{"id":"2002.01793","title":"Proximity Preserving Binary Code using Signed Graph-Cut","created":"2020-02-05","cited_by_count":2},{"id":"2311.07427","title":"Boolean Variation and Boolean Logic BackPropagation","created":"2023-11-13","cited_by_count":2},{"id":"2202.03716","title":"Binary Neural Networks as a general-propose compute paradigm for on-device computer vision","created":"2022-02-08","cited_by_count":1}],"next_cursor":null}