{"list":"other","total":378,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"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":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"1711.09601","title":"Memory Aware Synapses: Learning what (not) to forget","created":"2017-11-27","cited_by_count":1105},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"1912.03817","title":"Machine Unlearning","created":"2019-12-09","cited_by_count":1061},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"2004.07211","title":"Dark Experience for General Continual Learning: a Strong, Simple Baseline","created":"2020-04-15","cited_by_count":911},{"id":"1711.05769","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","created":"2017-11-15","cited_by_count":898},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"1801.10112","title":"Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence","created":"2018-01-30","cited_by_count":742},{"id":"1905.13260","title":"Large Scale Incremental Learning","created":"2019-05-30","cited_by_count":732},{"id":"1708.01547","title":"Lifelong Learning with Dynamically Expandable Networks","created":"2017-08-04","cited_by_count":694},{"id":"1801.01423","title":"Overcoming catastrophic forgetting with hard attention to the task","created":"2018-01-04","cited_by_count":681},{"id":"2204.04799","title":"DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning","created":"2022-04-10","cited_by_count":642},{"id":"1911.04933","title":"Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks","created":"2019-11-12","cited_by_count":618},{"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":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"1903.08671","title":"Gradient based sample selection for online continual learning","created":"2019-03-20","cited_by_count":571},{"id":"1810.11910","title":"Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference","created":"2018-10-29","cited_by_count":521},{"id":"1805.06370","title":"Progress & Compress: A scalable framework for continual learning","created":"2018-05-16","cited_by_count":520},{"id":"2211.13218","title":"CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning","created":"2022-11-23","cited_by_count":450},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434},{"id":"1912.08795","title":"Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion","created":"2019-12-18","cited_by_count":423},{"id":"2006.04388","title":"Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection","created":"2020-06-08","cited_by_count":409},{"id":"1908.04742","title":"Online Continual Learning with Maximally Interfered Retrieval","created":"2019-08-11","cited_by_count":379},{"id":"1611.06194","title":"Expert Gate: Lifelong Learning with a Network of Experts","created":"2016-11-18","cited_by_count":372},{"id":"1910.07104","title":"Orthogonal Gradient Descent for Continual Learning","created":"2019-10-15","cited_by_count":369},{"id":"2008.11687","title":"What is being transferred in transfer learning?","created":"2020-08-26","cited_by_count":368},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"2103.16788","title":"DER: Dynamically Expandable Representation for Class Incremental Learning","created":"2021-03-31","cited_by_count":355},{"id":"2103.09762","title":"Gradient Projection Memory for Continual Learning","created":"2021-03-17","cited_by_count":348},{"id":"1710.10628","title":"Variational Continual Learning","created":"2017-10-29","cited_by_count":339},{"id":"2006.09965","title":"High-Fidelity Generative Image Compression","created":"2020-06-17","cited_by_count":338},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"1904.00310","title":"Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting","created":"2019-03-31","cited_by_count":302},{"id":"2103.02603","title":"Towards Open World Object Detection","created":"2021-03-03","cited_by_count":297},{"id":"2111.11326","title":"DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion","created":"2021-11-22","cited_by_count":291},{"id":"1705.03550","title":"CORe50: a New Dataset and Benchmark for Continuous Object Recognition","created":"2017-05-09","cited_by_count":289},{"id":"1911.07053","title":"Maintaining Discrimination and Fairness in Class Incremental Learning","created":"2019-11-16","cited_by_count":283},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1906.00695","title":"Continual learning with hypernetworks","created":"2019-06-03","cited_by_count":273},{"id":"2103.17230","title":"Rainbow Memory: Continual Learning with a Memory of Diverse Samples","created":"2021-03-31","cited_by_count":273},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"2004.10956","title":"Few-Shot Class-Incremental Learning","created":"2020-04-23","cited_by_count":251},{"id":"1811.08051","title":"Learning without Memorizing","created":"2018-11-20","cited_by_count":250},{"id":"2207.12819","title":"S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning","created":"2022-07-26","cited_by_count":246},{"id":"2101.10423","title":"Online Continual Learning in Image Classification: An Empirical Survey","created":"2021-01-25","cited_by_count":245},{"id":"2106.14413","title":"Co$^2$L: Contrastive Continual Learning","created":"2021-06-28","cited_by_count":244},{"id":"1703.08475","title":"Overcoming Catastrophic Forgetting by Incremental Moment Matching","created":"2017-03-24","cited_by_count":243},{"id":"1802.10269","title":"Selective Experience Replay for Lifelong Learning","created":"2018-02-28","cited_by_count":241},{"id":"2004.00440","title":"Semantic Drift Compensation for Class-Incremental Learning","created":"2020-04-01","cited_by_count":241},{"id":"1907.12412","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","created":"2019-07-29","cited_by_count":231},{"id":"2204.04662","title":"FOSTER: Feature Boosting and Compression for Class-Incremental Learning","created":"2022-04-10","cited_by_count":229},{"id":"1810.12488","title":"Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines","created":"2018-10-30","cited_by_count":228},{"id":"2006.14769","title":"Supermasks in Superposition","created":"2020-06-26","cited_by_count":227},{"id":"1812.03596","title":"Task-Free Continual Learning","created":"2018-12-10","cited_by_count":221},{"id":"2002.10211","title":"Mnemonics Training: Multi-Class Incremental Learning without Forgetting","created":"2020-02-24","cited_by_count":221},{"id":"2104.05025","title":"New Insights on Reducing Abrupt Representation Change in Online Continual Learning","created":"2021-04-11","cited_by_count":219},{"id":"1708.06977","title":"Incremental Learning of Object Detectors without Catastrophic Forgetting","created":"2017-08-23","cited_by_count":208},{"id":"1910.06562","title":"Compacting, Picking and Growing for Unforgetting Continual Learning","created":"2019-10-15","cited_by_count":207},{"id":"1805.07810","title":"Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting","created":"2018-05-20","cited_by_count":201},{"id":"1910.02509","title":"REMIND Your Neural Network to Prevent Catastrophic Forgetting","created":"2019-10-06","cited_by_count":197},{"id":"2301.12314","title":"Progressive Prompts: Continual Learning for Language Models","created":"2023-01-29","cited_by_count":197},{"id":"2006.03875","title":"Coresets via Bilevel Optimization for Continual Learning and Streaming","created":"2020-06-06","cited_by_count":192},{"id":"2002.00718","title":"Modeling the Background for Incremental Learning in Semantic Segmentation","created":"2020-02-03","cited_by_count":190},{"id":"1905.12588","title":"Meta-Learning Representations for Continual Learning","created":"2019-05-29","cited_by_count":189}],"next_cursor":"100"}