{"list":"other","total":92,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"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":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1607.02533","title":"Adversarial examples in the physical world","created":"2016-07-08","cited_by_count":1769},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"id":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"id":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"2001.03994","title":"Fast is better than free: Revisiting adversarial training","created":"2020-01-12","cited_by_count":727},{"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":"1904.12843","title":"Adversarial Training for Free!","created":"2019-04-29","cited_by_count":643},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"1711.00117","title":"Countering Adversarial Images using Input Transformations","created":"2017-10-31","cited_by_count":520},{"id":"2002.11569","title":"Overfitting in adversarially robust deep learning","created":"2020-02-26","cited_by_count":506},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"1704.01155","title":"Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks","created":"2017-04-04","cited_by_count":486},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1711.01991","title":"Mitigating Adversarial Effects Through Randomization","created":"2017-11-06","cited_by_count":383},{"id":"1712.02976","title":"Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser","created":"2017-12-08","cited_by_count":329},{"id":"1804.11285","title":"Adversarially Robust Generalization Requires More Data","created":"2018-04-30","cited_by_count":318},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"id":"2002.11242","title":"Attacks Which Do Not Kill Training Make Adversarial Learning Stronger","created":"2020-02-26","cited_by_count":243},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"2010.00467","title":"Bag of Tricks for Adversarial Training","created":"2020-10-01","cited_by_count":200},{"id":"2010.01736","title":"Geometry-aware Instance-reweighted Adversarial Training","created":"2020-10-05","cited_by_count":198},{"id":"1608.00853","title":"A study of the effect of JPG compression on adversarial images","created":"2016-08-02","cited_by_count":197},{"id":"1902.05967","title":"Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization","created":"2019-02-15","cited_by_count":189},{"id":"1705.08475","title":"Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation","created":"2017-05-23","cited_by_count":185},{"id":"1811.09716","title":"Robustness via curvature regularization, and vice versa","created":"2018-11-23","cited_by_count":175},{"id":"1803.01442","title":"Stochastic Activation Pruning for Robust Adversarial Defense","created":"2018-03-05","cited_by_count":171},{"id":"1909.11957","title":"Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks","created":"2019-09-26","cited_by_count":160},{"id":"1712.00673","title":"Towards Robust Neural Networks via Random Self-ensemble","created":"2017-12-02","cited_by_count":159},{"id":"2003.12862","title":"Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning","created":"2020-03-28","cited_by_count":153},{"id":"2010.13337","title":"Robust Pre-Training by Adversarial Contrastive Learning","created":"2020-10-26","cited_by_count":144},{"id":"1906.06032","title":"Adversarial Training Can Hurt Generalization","created":"2019-06-14","cited_by_count":132},{"id":"2102.06790","title":"A Unified Lottery Ticket Hypothesis for Graph Neural Networks","created":"2021-02-12","cited_by_count":118},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110},{"id":"1903.12561","title":"Adversarial Robustness vs Model Compression, or Both?","created":"2019-03-29","cited_by_count":98},{"id":"2012.06908","title":"The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models","created":"2020-12-12","cited_by_count":91},{"id":"2106.03517","title":"Top-KAST: Top-K Always Sparse Training","created":"2021-06-07","cited_by_count":79},{"id":"2108.07969","title":"Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better","created":"2021-08-18","cited_by_count":79},{"id":"2003.02484","title":"Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalization","created":"2020-03-05","cited_by_count":73},{"id":"1810.09619","title":"Sparse DNNs with Improved Adversarial Robustness","created":"2018-10-23","cited_by_count":72},{"id":"1902.03538","title":"Model Compression with Adversarial Robustness: A Unified Optimization Framework","created":"2019-02-10","cited_by_count":71},{"id":"1906.10732","title":"The Difficulty of Training Sparse Neural Networks","created":"2019-06-25","cited_by_count":62},{"id":"2104.04448","title":"Relating Adversarially Robust Generalization to Flat Minima","created":"2021-04-09","cited_by_count":57},{"id":"1910.02366","title":"Splitting Steepest Descent for Growing Neural Architectures","created":"2019-10-06","cited_by_count":55},{"id":"2106.01606","title":"Exploring Memorization in Adversarial Training","created":"2021-06-03","cited_by_count":55},{"id":"1811.10716","title":"Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks","created":"2018-11-26","cited_by_count":48},{"id":"2001.01969","title":"Sparse Weight Activation Training","created":"2020-01-07","cited_by_count":45},{"id":"2002.10025","title":"Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference","created":"2020-02-24","cited_by_count":45},{"id":"2104.11832","title":"Playing Lottery Tickets with Vision and Language","created":"2021-04-23","cited_by_count":45},{"id":"2106.03225","title":"Efficient Lottery Ticket Finding: Less Data is More","created":"2021-06-06","cited_by_count":44},{"id":"2103.04623","title":"Consistency Regularization for Adversarial Robustness","created":"2021-03-08","cited_by_count":42},{"id":"1901.00532","title":"Adversarial Robustness May Be at Odds With Simplicity","created":"2019-01-02","cited_by_count":39},{"id":"1807.10272","title":"Evaluating and Understanding the Robustness of Adversarial Logit Pairing","created":"2018-07-26","cited_by_count":34},{"id":"1604.05978","title":"A topological insight into restricted Boltzmann machines","created":"2016-04-20","cited_by_count":32},{"id":"2106.00134","title":"GANs Can Play Lottery Tickets Too","created":"2021-05-31","cited_by_count":32},{"id":"1909.10147","title":"Robust Local Features for Improving the Generalization of Adversarial Training","created":"2019-09-23","cited_by_count":30},{"id":"2102.07861","title":"Low Curvature Activations Reduce Overfitting in Adversarial Training","created":"2021-02-15","cited_by_count":29},{"id":"2110.14068","title":"Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks","created":"2021-10-26","cited_by_count":29},{"id":"1810.12042","title":"Logit Pairing Methods Can Fool Gradient-Based Attacks","created":"2018-10-29","cited_by_count":27},{"id":"2202.04736","title":"Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets","created":"2022-02-09","cited_by_count":27},{"id":"2101.09048","title":"Selfish Sparse RNN Training","created":"2021-01-22","cited_by_count":26},{"id":"1906.06110","title":"Towards Compact and Robust Deep Neural Networks","created":"2019-06-14","cited_by_count":23},{"id":"1702.06763","title":"DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples","created":"2017-02-22","cited_by_count":22},{"id":"2009.10976","title":"Procrustes: a Dataflow and Accelerator for Sparse Deep Neural Network Training","created":"2020-09-23","cited_by_count":18},{"id":"2111.00162","title":"You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership","created":"2021-10-30","cited_by_count":18},{"id":"2003.10392","title":"Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting","created":"2020-03-23","cited_by_count":14},{"id":"2107.02306","title":"Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity","created":"2021-07-05","cited_by_count":14},{"id":"1902.11019","title":"Towards Understanding Adversarial Examples Systematically: Exploring Data Size, Task and Model Factors","created":"2019-02-28","cited_by_count":10},{"id":"2004.05884","title":"Adversarial Weight Perturbation Helps Robust Generalization","created":"2020-04-13","cited_by_count":10},{"id":"2003.05733","title":"Towards Practical Lottery Ticket Hypothesis for Adversarial Training","created":"2020-03-06","cited_by_count":9},{"id":"2008.12338","title":"Adversarially Robust Learning via Entropic Regularization","created":"2020-08-27","cited_by_count":9},{"id":"2102.07327","title":"Guided Interpolation for Adversarial Training","created":"2021-02-15","cited_by_count":8},{"id":"2103.11589","title":"Adversarially Optimized Mixup for Robust Classification","created":"2021-03-22","cited_by_count":7},{"id":"1906.00698","title":"Adversarial Risk Bounds for Neural Networks through Sparsity based Compression","created":"2019-06-03","cited_by_count":4},{"id":"2106.05453","title":"Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training","created":"2021-06-10","cited_by_count":3}],"next_cursor":null}