{"list":"other","total":71,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"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":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"1711.09601","title":"Memory Aware Synapses: Learning what (not) to forget","created":"2017-11-27","cited_by_count":1105},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"1801.10112","title":"Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence","created":"2018-01-30","cited_by_count":742},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"1905.13260","title":"Large Scale Incremental Learning","created":"2019-05-30","cited_by_count":732},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2204.04799","title":"DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning","created":"2022-04-10","cited_by_count":642},{"id":"1807.09536","title":"End-to-End Incremental Learning","created":"2018-07-25","cited_by_count":597},{"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":"2010.15277","title":"Class-incremental learning: survey and performance evaluation on image classification","created":"2020-10-28","cited_by_count":449},{"id":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","created":"2019-12-05","cited_by_count":443},{"id":"1910.04867","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","created":"2019-10-01","cited_by_count":425},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390},{"id":"2103.16788","title":"DER: Dynamically Expandable Representation for Class Incremental Learning","created":"2021-03-31","cited_by_count":355},{"id":"1807.01622","title":"Neural Processes","created":"2018-07-04","cited_by_count":311},{"id":"2111.11326","title":"DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion","created":"2021-11-22","cited_by_count":291},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267},{"id":"2305.18292","title":"Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models","created":"2023-05-29","cited_by_count":261},{"id":"2303.07338","title":"Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need","created":"2023-03-13","cited_by_count":184},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182},{"id":"2307.02251","title":"RanPAC: Random Projections and Pre-trained Models for Continual Learning","created":"2023-07-05","cited_by_count":164},{"id":"2007.07400","title":"Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics","created":"2020-07-14","cited_by_count":161},{"id":"1805.09733","title":"Towards Robust Evaluations of Continual Learning","created":"2018-05-24","cited_by_count":148},{"id":"2304.06027","title":"Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA","created":"2023-04-12","cited_by_count":141},{"id":"2004.14070","title":"Continual Deep Learning by Functional Regularisation of Memorable Past","created":"2020-04-29","cited_by_count":105},{"id":"2105.06868","title":"Priors in Bayesian Deep Learning: A Review","created":"2021-05-14","cited_by_count":101},{"id":"2107.04384","title":"Continual Learning in the Teacher-Student Setup: Impact of Task Similarity","created":"2021-07-09","cited_by_count":88},{"id":"2104.07446","title":"Rehearsal revealed: The limits and merits of revisiting samples in continual learning","created":"2021-04-15","cited_by_count":76},{"id":"2206.09059","title":"CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks","created":"2022-06-18","cited_by_count":68},{"id":"2210.03114","title":"CLIP model is an Efficient Continual Learner","created":"2022-10-06","cited_by_count":65},{"id":"2111.07736","title":"Continual Learning via Local Module Composition","created":"2021-11-15","cited_by_count":63},{"id":"2205.13452","title":"Continual evaluation for lifelong learning: Identifying the stability gap","created":"2022-05-26","cited_by_count":56},{"id":"2209.09476","title":"SparCL: Sparse Continual Learning on the Edge","created":"2022-09-20","cited_by_count":55},{"id":"2210.02390","title":"Bayesian Prompt Learning for Image-Language Model Generalization","created":"2022-10-05","cited_by_count":51},{"id":"2305.11488","title":"AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning","created":"2023-05-19","cited_by_count":46},{"id":"2111.04578","title":"Improved Regularization and Robustness for Fine-tuning in Neural Networks","created":"2021-11-08","cited_by_count":45},{"id":"2305.07437","title":"Continual Vision-Language Representation Learning with Off-Diagonal Information","created":"2023-05-11","cited_by_count":40},{"id":"2210.04174","title":"Grow and Merge: A Unified Framework for Continuous Categories Discovery","created":"2022-10-09","cited_by_count":33},{"id":"1912.03049","title":"Regularization Shortcomings for Continual Learning","created":"2019-12-06","cited_by_count":32},{"id":"2202.10203","title":"Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning","created":"2022-02-21","cited_by_count":29},{"id":"2203.13167","title":"Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularization","created":"2022-03-24","cited_by_count":23},{"id":"2104.09396","title":"Continual Learning in Sensor-based Human Activity Recognition: an Empirical Benchmark Analysis","created":"2021-04-19","cited_by_count":21},{"id":"2310.19272","title":"NPCL: Neural Processes for Uncertainty-Aware Continual Learning","created":"2023-10-30","cited_by_count":14},{"id":"2306.01904","title":"Overcoming the Stability Gap in Continual Learning","created":"2023-06-02","cited_by_count":13},{"id":"2204.05462","title":"Out-Of-Distribution Detection In Unsupervised Continual Learning","created":"2022-04-12","cited_by_count":10},{"id":"2403.10853","title":"GenOL: Generating Diverse Examples for Name-only Online Learning","created":"2024-03-16","cited_by_count":9},{"id":"2304.02168","title":"I2I: Initializing Adapters with Improvised Knowledge","created":"2023-04-04","cited_by_count":7},{"id":"2212.08123","title":"Bayesian posterior approximation with stochastic ensembles","created":"2022-12-15","cited_by_count":5}],"next_cursor":null}