{"list":"other","total":58,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1711.09601","title":"Memory Aware Synapses: Learning what (not) to forget","created":"2017-11-27","cited_by_count":1105},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1805.12152","title":"Robustness May Be at Odds with Accuracy","created":"2018-05-30","cited_by_count":880},{"id":"1905.13260","title":"Large Scale Incremental Learning","created":"2019-05-30","cited_by_count":732},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"1312.6211","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","created":"2013-12-21","cited_by_count":722},{"id":"1904.07734","title":"Three scenarios for continual learning","created":"2019-04-15","cited_by_count":614},{"id":"1807.09536","title":"End-to-End Incremental Learning","created":"2018-07-25","cited_by_count":597},{"id":"1810.11910","title":"Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference","created":"2018-10-29","cited_by_count":521},{"id":"1805.12018","title":"Generalizing to Unseen Domains via Adversarial Data Augmentation","created":"2018-05-30","cited_by_count":451},{"id":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","created":"2019-12-05","cited_by_count":443},{"id":"1611.06194","title":"Expert Gate: Lifelong Learning with a Network of Experts","created":"2016-11-18","cited_by_count":372},{"id":"2103.16788","title":"DER: Dynamically Expandable Representation for Class Incremental Learning","created":"2021-03-31","cited_by_count":355},{"id":"2111.11326","title":"DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion","created":"2021-11-22","cited_by_count":291},{"id":"2002.10211","title":"Mnemonics Training: Multi-Class Incremental Learning without Forgetting","created":"2020-02-24","cited_by_count":221},{"id":"1910.06562","title":"Compacting, Picking and Growing for Unforgetting Continual Learning","created":"2019-10-15","cited_by_count":207},{"id":"1905.12588","title":"Meta-Learning Representations for Continual Learning","created":"2019-05-29","cited_by_count":189},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145},{"id":"1805.03857","title":"Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration","created":"2018-05-10","cited_by_count":115},{"id":"1810.13166","title":"Don't forget, there is more than forgetting: new metrics for Continual Learning","created":"2018-10-31","cited_by_count":115},{"id":"2110.04301","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","created":"2021-10-08","cited_by_count":114},{"id":"2204.00895","title":"Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation","created":"2022-04-02","cited_by_count":113},{"id":"2004.09199","title":"Generative Feature Replay For Class-Incremental Learning","created":"2020-04-20","cited_by_count":109},{"id":"2105.07197","title":"Are Convolutional Neural Networks or Transformers more like human vision?","created":"2021-05-15","cited_by_count":109},{"id":"1906.02611","title":"Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation","created":"2019-06-06","cited_by_count":105},{"id":"2010.05981","title":"Shape-Texture Debiased Neural Network Training","created":"2020-10-12","cited_by_count":76},{"id":"2105.11144","title":"Improved OOD Generalization via Adversarial Training and Pre-training","created":"2021-05-24","cited_by_count":66},{"id":"2106.07171","title":"Examining and Combating Spurious Features under Distribution Shift","created":"2021-06-14","cited_by_count":65},{"id":"1703.06953","title":"Multi-style Generative Network for Real-time Transfer","created":"2017-03-20","cited_by_count":61},{"id":"2211.00789","title":"Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer","created":"2022-11-01","cited_by_count":59},{"id":"2008.04254","title":"Informative Dropout for Robust Representation Learning: A Shape-bias Perspective","created":"2020-08-10","cited_by_count":57},{"id":"2102.09517","title":"Essentials for Class Incremental Learning","created":"2021-02-18","cited_by_count":57},{"id":"2012.04104","title":"Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately","created":"2020-12-07","cited_by_count":52},{"id":"2101.11604","title":"Shape or Texture: Understanding Discriminative Features in CNNs","created":"2021-01-27","cited_by_count":52},{"id":"2209.03718","title":"The neuroconnectionist research programme","created":"2022-09-08","cited_by_count":48},{"id":"2206.00388","title":"Transfer without Forgetting","created":"2022-06-01","cited_by_count":44},{"id":"2210.06441","title":"How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization","created":"2022-10-12","cited_by_count":40},{"id":"2104.10093","title":"Class-Incremental Learning with Generative Classifiers","created":"2021-04-20","cited_by_count":39},{"id":"1802.03875","title":"Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks","created":"2018-02-12","cited_by_count":23},{"id":"2112.06103","title":"Improving Vision Transformers for Incremental Learning","created":"2021-12-12","cited_by_count":17},{"id":"2005.03490","title":"Generative Feature Replay with Orthogonal Weight Modification for Continual Learning","created":"2020-05-07","cited_by_count":10},{"id":"2106.08285","title":"Multi-StyleGAN: Towards Image-Based Simulation of Time-Lapse Live-Cell Microscopy","created":"2021-06-15","cited_by_count":4}],"next_cursor":null}