{"list":"other","total":55,"rows":[{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"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":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1711.10925","title":"Deep Image Prior","created":"2017-11-29","cited_by_count":1098},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"2004.10568","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","created":"2020-04-22","cited_by_count":621},{"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":"1806.08342","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","created":"2018-06-21","cited_by_count":521},{"id":"1805.06085","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","created":"2018-05-16","cited_by_count":467},{"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":"1912.08795","title":"Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion","created":"2019-12-18","cited_by_count":423},{"id":"1606.05908","title":"Tutorial on Variational Autoencoders","created":"2016-06-19","cited_by_count":409},{"id":"1412.0035","title":"Understanding Deep Image Representations by Inverting Them","created":"2014-11-26","cited_by_count":403},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1906.04721","title":"Data-Free Quantization Through Weight Equalization and Bias Correction","created":"2019-06-11","cited_by_count":336},{"id":"2001.00281","title":"ZeroQ: A Novel Zero Shot Quantization Framework","created":"2020-01-01","cited_by_count":269},{"id":"1801.01973","title":"A Note on the Inception Score","created":"2018-01-06","cited_by_count":226},{"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":"1904.01186","title":"Data-Free Learning of Student Networks","created":"2019-04-02","cited_by_count":204},{"id":"1902.06822","title":"Low-bit Quantization of Neural Networks for Efficient Inference","created":"2019-02-18","cited_by_count":193},{"id":"1911.05248","title":"What Do Compressed Deep Neural Networks Forget?","created":"2019-11-13","cited_by_count":171},{"id":"2010.03058","title":"Characterising Bias in Compressed Models","created":"2020-10-06","cited_by_count":167},{"id":"1901.09504","title":"Improving Neural Network Quantization without Retraining using Outlier Channel Splitting","created":"2019-01-28","cited_by_count":151},{"id":"1711.11294","title":"Towards Accurate Binary Convolutional Neural Network","created":"2017-11-30","cited_by_count":149},{"id":"1710.07535","title":"Data-Free Knowledge Distillation for Deep Neural Networks","created":"2017-10-19","cited_by_count":136},{"id":"1905.09768","title":"Zero-shot Knowledge Transfer via Adversarial Belief Matching","created":"2019-05-23","cited_by_count":129},{"id":"1905.08114","title":"Zero-Shot Knowledge Distillation in Deep Networks","created":"2019-05-20","cited_by_count":121},{"id":"2003.11535","title":"Training Binary Neural Networks with Real-to-Binary Convolutions","created":"2020-03-25","cited_by_count":112},{"id":"2005.03161","title":"MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation","created":"2020-05-06","cited_by_count":99},{"id":"2003.03603","title":"Generative Low-bitwidth Data Free Quantization","created":"2020-03-07","cited_by_count":88},{"id":"2005.04136","title":"Data-Free Network Quantization With Adversarial Knowledge Distillation","created":"2020-05-08","cited_by_count":80},{"id":"1807.09499","title":"How good is my GAN?","created":"2018-07-25","cited_by_count":74},{"id":"1611.01673","title":"Generative Multi-Adversarial Networks","created":"2016-11-05","cited_by_count":60},{"id":"1511.04561","title":"8-Bit Approximations for Parallelism in Deep Learning","created":"2015-11-14","cited_by_count":56},{"id":"1912.01274","title":"The Knowledge Within: Methods for Data-Free Model Compression","created":"2019-12-03","cited_by_count":54},{"id":"1810.05723","title":"Post-training 4-bit quantization of convolution networks for rapid-deployment","created":"2018-10-02","cited_by_count":42},{"id":"1907.06627","title":"Batch-Shaping for Learning Conditional Channel Gated Networks","created":"2019-07-15","cited_by_count":42},{"id":"1511.06488","title":"Resiliency of Deep Neural Networks under Quantization","created":"2015-11-20","cited_by_count":35},{"id":"1906.03193","title":"Fighting Quantization Bias With Bias","created":"2019-06-07","cited_by_count":30},{"id":"2002.06517","title":"BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activations","created":"2020-02-16","cited_by_count":23},{"id":"1809.03368","title":"Probabilistic Binary Neural Networks","created":"2018-09-10","cited_by_count":21},{"id":"1905.07072","title":"Dream Distillation: A Data-Independent Model Compression Framework","created":"2019-05-17","cited_by_count":19}],"next_cursor":null}