{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1711.09601","title":"Memory Aware Synapses: Learning what (not) to forget","created":"2017-11-27","cited_by_count":1105},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"2004.07211","title":"Dark Experience for General Continual Learning: a Strong, Simple Baseline","created":"2020-04-15","cited_by_count":911},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"id":"1801.10112","title":"Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence","created":"2018-01-30","cited_by_count":742},{"id":"1708.01547","title":"Lifelong Learning with Dynamically Expandable Networks","created":"2017-08-04","cited_by_count":694},{"id":"1811.12833","title":"ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation","created":"2018-11-30","cited_by_count":623},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"2009.09796","title":"Multi-Task Learning with Deep Neural Networks: A Survey","created":"2020-09-10","cited_by_count":375},{"id":"1910.07104","title":"Orthogonal Gradient Descent for Continual Learning","created":"2019-10-15","cited_by_count":369},{"id":"1512.07108","title":"Recent Advances in Convolutional Neural Networks","created":"2015-12-22","cited_by_count":360},{"id":"1811.08051","title":"Learning without Memorizing","created":"2018-11-20","cited_by_count":250},{"id":"2106.14413","title":"Co$^2$L: Contrastive Continual Learning","created":"2021-06-28","cited_by_count":244},{"id":"1912.12854","title":"Pareto Multi-Task Learning","created":"2019-12-30","cited_by_count":224},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215},{"id":"2010.06808","title":"Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout","created":"2020-10-14","cited_by_count":201},{"id":"1901.08428","title":"Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group","created":"2019-01-24","cited_by_count":134},{"id":"1911.12207","title":"Orthogonal Convolutional Neural Networks","created":"2019-11-27","cited_by_count":123},{"id":"2303.06628","title":"Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models","created":"2023-03-12","cited_by_count":112},{"id":"1705.04228","title":"Incremental Learning Through Deep Adaptation","created":"2017-05-11","cited_by_count":108},{"id":"1611.00035","title":"Full-Capacity Unitary Recurrent Neural Networks","created":"2016-10-31","cited_by_count":94},{"id":"1709.06079","title":"Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks","created":"2017-09-16","cited_by_count":92},{"id":"2305.19000","title":"Independent Component Alignment for Multi-Task Learning","created":"2023-05-30","cited_by_count":70},{"id":"2006.15294","title":"Gradient-based Editing of Memory Examples for Online Task-free Continual Learning","created":"2020-06-27","cited_by_count":62},{"id":"1703.01827","title":"All You Need is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks with Orthonormality and Modulation","created":"2017-03-06","cited_by_count":58},{"id":"2105.12374","title":"Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks","created":"2021-05-26","cited_by_count":56},{"id":"1805.06576","title":"Mad Max: Affine Spline Insights into Deep Learning","created":"2018-05-17","cited_by_count":55},{"id":"2201.03299","title":"Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks","created":"2022-01-10","cited_by_count":55},{"id":"2105.07561","title":"Layerwise Optimization by Gradient Decomposition for Continual Learning","created":"2021-05-17","cited_by_count":51},{"id":"2004.07941","title":"Continual Learning for Anomaly Detection in Surveillance Videos","created":"2020-04-15","cited_by_count":49},{"id":"2209.12241","title":"Exploring Example Influence in Continual Learning","created":"2022-09-25","cited_by_count":44},{"id":"1605.07784","title":"Fast Algorithms for Robust PCA via Gradient Descent","created":"2016-05-25","cited_by_count":39},{"id":"2009.01717","title":"Multi-Loss Weighting with Coefficient of Variations","created":"2020-09-03","cited_by_count":36},{"id":"2102.09468","title":"Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization","created":"2021-02-18","cited_by_count":31},{"id":"2004.00917","title":"Controllable Orthogonalization in Training DNNs","created":"2020-04-02","cited_by_count":30},{"id":"1611.06013","title":"Improving training of deep neural networks via Singular Value Bounding","created":"2016-11-18","cited_by_count":26},{"id":"2012.07236","title":"Multi-Domain Multi-Task Rehearsal for Lifelong Learning","created":"2020-12-14","cited_by_count":24},{"id":"1902.10424","title":"Single-frame Regularization for Temporally Stable CNNs","created":"2019-02-27","cited_by_count":21},{"id":"2105.10827","title":"Orthogonal Ensemble Networks for Biomedical Image Segmentation","created":"2021-05-22","cited_by_count":16},{"id":"2108.05623","title":"Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks","created":"2021-08-12","cited_by_count":16},{"id":"2203.05534","title":"AGCN: Augmented Graph Convolutional Network for Lifelong Multi-label Image Recognition","created":"2022-03-10","cited_by_count":16},{"id":"1909.11763","title":"Improved Schemes for Episodic Memory-based Lifelong Learning","created":"2019-09-25","cited_by_count":7},{"id":"2402.08182","title":"Variational Continual Test-Time Adaptation","created":"2024-02-13","cited_by_count":7},{"id":"2110.09374","title":"Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation for Few-Shot Learning","created":"2021-10-18","cited_by_count":3},{"id":"1807.02799","title":"Distillation Techniques for Pseudo-rehearsal Based Incremental Learning","created":"2018-07-08","cited_by_count":2}],"next_cursor":null}