{"list":"other","total":103,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1607.02533","title":"Adversarial examples in the physical world","created":"2016-07-08","cited_by_count":1769},{"id":"1807.03888","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","created":"2018-07-10","cited_by_count":1485},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"1910.09457","title":"Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods","created":"2019-10-21","cited_by_count":913},{"id":"1711.05769","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","created":"2017-11-15","cited_by_count":898},{"id":"2011.06225","title":"A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges","created":"2020-11-12","cited_by_count":819},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"1806.01768","title":"Evidential Deep Learning to Quantify Classification Uncertainty","created":"2018-06-05","cited_by_count":732},{"id":"1705.08039","title":"Poincar\\'e Embeddings for Learning Hierarchical Representations","created":"2017-05-22","cited_by_count":684},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"1904.07734","title":"Three scenarios for continual learning","created":"2019-04-15","cited_by_count":614},{"id":"1906.03671","title":"Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds","created":"2019-06-09","cited_by_count":610},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"1802.10501","title":"Predictive Uncertainty Estimation via Prior Networks","created":"2018-02-28","cited_by_count":557},{"id":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1803.00676","title":"Meta-Learning for Semi-Supervised Few-Shot Classification","created":"2018-03-02","cited_by_count":456},{"id":"1906.02845","title":"Likelihood Ratios for Out-of-Distribution Detection","created":"2019-06-07","cited_by_count":453},{"id":"1812.01718","title":"Deep Learning for Classical Japanese Literature","created":"2018-12-03","cited_by_count":422},{"id":"1910.12933","title":"Hyperbolic Graph Convolutional Neural Networks","created":"2019-10-28","cited_by_count":402},{"id":"1711.09325","title":"Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples","created":"2017-11-26","cited_by_count":389},{"id":"1910.12656","title":"Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration","created":"2019-10-28","cited_by_count":364},{"id":"2007.06823","title":"Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users","created":"2020-07-14","cited_by_count":338},{"id":"1905.03677","title":"Learning Loss for Active Learning","created":"2019-05-09","cited_by_count":336},{"id":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"id":"1812.05720","title":"Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem","created":"2018-12-13","cited_by_count":323},{"id":"1608.06019","title":"Domain Separation Networks","created":"2016-08-22","cited_by_count":320},{"id":"1810.09502","title":"How to train your MAML","created":"2018-10-22","cited_by_count":309},{"id":"1905.11001","title":"On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks","created":"2019-05-27","cited_by_count":305},{"id":"1904.00370","title":"Variational Adversarial Active Learning","created":"2019-03-31","cited_by_count":284},{"id":"1906.00695","title":"Continual learning with hypernetworks","created":"2019-06-03","cited_by_count":273},{"id":"1906.00817","title":"Zero-Shot Semantic Segmentation","created":"2019-06-03","cited_by_count":245},{"id":"1904.02239","title":"Hyperbolic Image Embeddings","created":"2019-04-03","cited_by_count":221},{"id":"1606.01885","title":"Learning to Optimize","created":"2016-06-06","cited_by_count":195},{"id":"2007.05566","title":"Contrastive Training for Improved Out-of-Distribution Detection","created":"2020-07-10","cited_by_count":186},{"id":"1605.05395","title":"Learning Deep Representations of Fine-grained Visual Descriptions","created":"2016-05-17","cited_by_count":182},{"id":"2006.06958","title":"Understanding the Role of Training Regimes in Continual Learning","created":"2020-06-12","cited_by_count":180},{"id":"1812.05418","title":"DLOW: Domain Flow for Adaptation and Generalization","created":"2018-12-13","cited_by_count":177},{"id":"2006.09239","title":"Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts","created":"2020-06-16","cited_by_count":164},{"id":"2007.09222","title":"Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation","created":"2020-07-17","cited_by_count":142},{"id":"2003.08607","title":"Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering","created":"2020-03-19","cited_by_count":140},{"id":"1312.5650","title":"Zero-Shot Learning by Convex Combination of Semantic Embeddings","created":"2013-12-19","cited_by_count":135},{"id":"2003.13183","title":"Gradually Vanishing Bridge for Adversarial Domain Adaptation","created":"2020-03-30","cited_by_count":130},{"id":"1909.11825","title":"Unsupervised Domain Adaptation through Self-Supervision","created":"2019-09-26","cited_by_count":116},{"id":"1805.08206","title":"Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers","created":"2018-05-21","cited_by_count":113},{"id":"1912.09393","title":"Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks","created":"2019-12-19","cited_by_count":113},{"id":"1908.04951","title":"Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy","created":"2019-08-14","cited_by_count":112},{"id":"2004.14070","title":"Continual Deep Learning by Functional Regularisation of Memorable Past","created":"2020-04-29","cited_by_count":105},{"id":"1909.00025","title":"Meta-Learning with Warped Gradient Descent","created":"2019-08-30","cited_by_count":98},{"id":"1912.11976","title":"HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptation","created":"2019-12-27","cited_by_count":89},{"id":"2006.07543","title":"GAN Memory with No Forgetting","created":"2020-06-13","cited_by_count":84},{"id":"1810.02334","title":"Unsupervised Learning via Meta-Learning","created":"2018-10-04","cited_by_count":82},{"id":"1911.12036","title":"Discriminative Adversarial Domain Adaptation","created":"2019-11-27","cited_by_count":74},{"id":"1905.05301","title":"Hierarchically Structured Meta-learning","created":"2019-05-13","cited_by_count":68},{"id":"1909.03360","title":"Episode-based Prototype Generating Network for Zero-Shot Learning","created":"2019-09-08","cited_by_count":66},{"id":"2006.04996","title":"Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation","created":"2020-06-09","cited_by_count":60},{"id":"1812.03973","title":"Bayesian Layers: A Module for Neural Network Uncertainty","created":"2018-12-10","cited_by_count":57},{"id":"1904.11643","title":"Bayesian Generative Active Deep Learning","created":"2019-04-26","cited_by_count":57},{"id":"2004.00666","title":"Generalized Zero-Shot Learning Via Over-Complete Distribution","created":"2020-04-01","cited_by_count":56},{"id":"1911.07982","title":"Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling","created":"2019-11-18","cited_by_count":53},{"id":"1901.11058","title":"HyperGAN: A Generative Model for Diverse, Performant Neural Networks","created":"2019-01-30","cited_by_count":51},{"id":"2004.03459","title":"Hierarchical Image Classification using Entailment Cone Embeddings","created":"2020-04-02","cited_by_count":46},{"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":"1805.08440","title":"Classification Uncertainty of Deep Neural Networks Based on Gradient Information","created":"2018-05-22","cited_by_count":43},{"id":"2005.06717","title":"Domain Conditioned Adaptation Network","created":"2020-05-14","cited_by_count":43},{"id":"2006.04183","title":"Uncertainty-Aware Deep Classifiers using Generative Models","created":"2020-06-07","cited_by_count":41},{"id":"2010.00352","title":"Meta-Consolidation for Continual Learning","created":"2020-10-01","cited_by_count":40},{"id":"2003.05856","title":"Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning","created":"2020-03-12","cited_by_count":38},{"id":"2007.07695","title":"Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation","created":"2020-07-15","cited_by_count":35},{"id":"2006.08939","title":"Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition","created":"2020-06-16","cited_by_count":34},{"id":"1907.04523","title":"Dual Dynamic Inference: Enabling More Efficient, Adaptive and Controllable Deep Inference","created":"2019-07-10","cited_by_count":31},{"id":"1711.01297","title":"Implicit Weight Uncertainty in Neural Networks","created":"2017-11-03","cited_by_count":30},{"id":"1711.06114","title":"Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment","created":"2017-11-16","cited_by_count":29},{"id":"1808.04505","title":"Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding","created":"2018-08-14","cited_by_count":28},{"id":"2003.00402","title":"Why is the Mahalanobis Distance Effective for Anomaly Detection?","created":"2020-03-01","cited_by_count":28},{"id":"1904.01109","title":"Creativity Inspired Zero-Shot Learning","created":"2019-04-01","cited_by_count":27},{"id":"1908.07235","title":"Density estimation in representation space to predict model uncertainty","created":"2019-08-20","cited_by_count":27},{"id":"1905.07435","title":"Alpha MAML: Adaptive Model-Agnostic Meta-Learning","created":"2019-05-17","cited_by_count":25},{"id":"1902.00415","title":"Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation","created":"2019-02-01","cited_by_count":23},{"id":"2010.02053","title":"A Fully Hyperbolic Neural Model for Hierarchical Multi-Class Classification","created":"2020-10-05","cited_by_count":23},{"id":"1812.01054","title":"Transferring Knowledge across Learning Processes","created":"2018-12-03","cited_by_count":22},{"id":"1907.05570","title":"Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning","created":"2019-07-12","cited_by_count":20},{"id":"2011.14540","title":"Heuristic Domain Adaptation","created":"2020-11-30","cited_by_count":19},{"id":"1706.07642","title":"A Variance Maximization Criterion for Active Learning","created":"2017-06-23","cited_by_count":9},{"id":"1906.06166","title":"Online Active Learning of Reject Option Classifiers","created":"2019-06-14","cited_by_count":9},{"id":"2010.06890","title":"Identifying Wrongly Predicted Samples: A Method for Active Learning","created":"2020-10-14","cited_by_count":8},{"id":"2005.08622","title":"Learn Class Hierarchy using Convolutional Neural Networks","created":"2020-05-18","cited_by_count":7},{"id":"2006.08914","title":"Calibrating Deep Neural Network Classifiers on Out-of-Distribution Datasets","created":"2020-06-16","cited_by_count":7},{"id":"2005.03188","title":"Active Learning with Multiple Kernels","created":"2020-05-07","cited_by_count":6},{"id":"2007.00051","title":"Extracurricular Learning: Knowledge Transfer Beyond Empirical Distribution","created":"2020-06-30","cited_by_count":4},{"id":"1809.09574","title":"Combined convolutional and recurrent neural networks for hierarchical classification of images","created":"2018-09-25","cited_by_count":3}],"next_cursor":"100"}