{"list":"other","total":106,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"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":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"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":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"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":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"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":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"1708.01547","title":"Lifelong Learning with Dynamically Expandable Networks","created":"2017-08-04","cited_by_count":694},{"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":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"1903.08671","title":"Gradient based sample selection for online continual learning","created":"2019-03-20","cited_by_count":571},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"2111.12797","title":"ReAct: Out-of-distribution Detection With Rectified Activations","created":"2021-11-24","cited_by_count":486},{"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":"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":"2302.12400","title":"Towards Stable Test-Time Adaptation in Dynamic Wild World","created":"2023-02-24","cited_by_count":415},{"id":"2103.16788","title":"DER: Dynamically Expandable Representation for Class Incremental Learning","created":"2021-03-31","cited_by_count":355},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294},{"id":"2111.11326","title":"DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion","created":"2021-11-22","cited_by_count":291},{"id":"1911.07053","title":"Maintaining Discrimination and Fairness in Class Incremental Learning","created":"2019-11-16","cited_by_count":283},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260},{"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":"2004.00440","title":"Semantic Drift Compensation for Class-Incremental Learning","created":"2020-04-01","cited_by_count":241},{"id":"2204.04662","title":"FOSTER: Feature Boosting and Compression for Class-Incremental Learning","created":"2022-04-10","cited_by_count":229},{"id":"2002.10211","title":"Mnemonics Training: Multi-Class Incremental Learning without Forgetting","created":"2020-02-24","cited_by_count":221},{"id":"2302.03648","title":"Class-Incremental Learning: A Survey","created":"2023-02-07","cited_by_count":209},{"id":"1805.12369","title":"Reinforced Continual Learning","created":"2018-05-31","cited_by_count":186},{"id":"2006.06958","title":"Understanding the Role of Training Regimes in Continual Learning","created":"2020-06-12","cited_by_count":180},{"id":"2303.05118","title":"SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model","created":"2023-03-09","cited_by_count":180},{"id":"1903.07864","title":"Class-incremental Learning via Deep Model Consolidation","created":"2019-03-19","cited_by_count":173},{"id":"2205.13218","title":"A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning","created":"2022-05-26","cited_by_count":154},{"id":"2010.05063","title":"Adaptive Aggregation Networks for Class-Incremental Learning","created":"2020-10-10","cited_by_count":149},{"id":"2205.01397","title":"Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)","created":"2022-05-03","cited_by_count":138},{"id":"2206.04673","title":"Neural Prompt Search","created":"2022-06-09","cited_by_count":135},{"id":"2212.03145","title":"FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer","created":"2022-12-06","cited_by_count":133},{"id":"2106.09701","title":"Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning","created":"2021-06-17","cited_by_count":131},{"id":"2203.06953","title":"Forward Compatible Few-Shot Class-Incremental Learning","created":"2022-03-14","cited_by_count":127},{"id":"2203.11473","title":"Federated Class-Incremental Learning","created":"2022-03-22","cited_by_count":127},{"id":"2106.10731","title":"Neighborhood Contrastive Learning for Novel Class Discovery","created":"2021-06-20","cited_by_count":121},{"id":"2103.01737","title":"Distilling Causal Effect of Data in Class-Incremental Learning","created":"2021-03-02","cited_by_count":117},{"id":"2204.00895","title":"Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation","created":"2022-04-02","cited_by_count":113},{"id":"2004.00713","title":"Memory-Efficient Incremental Learning Through Feature Adaptation","created":"2020-04-01","cited_by_count":107},{"id":"2003.04668","title":"Incremental Few-Shot Object Detection","created":"2020-03-10","cited_by_count":102},{"id":"2203.17030","title":"Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks","created":"2022-03-31","cited_by_count":88},{"id":"2104.08572","title":"On Learning the Geodesic Path for Incremental Learning","created":"2021-04-17","cited_by_count":85},{"id":"2112.12533","title":"PyCIL: A Python Toolbox for Class-Incremental Learning","created":"2021-12-23","cited_by_count":83},{"id":"2301.05792","title":"RMM: Reinforced Memory Management for Class-Incremental Learning","created":"2023-01-14","cited_by_count":66},{"id":"2006.15524","title":"MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning","created":"2020-06-28","cited_by_count":62},{"id":"2203.13104","title":"R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning","created":"2022-03-24","cited_by_count":59},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55},{"id":"2008.01411","title":"Memory Efficient Class-Incremental Learning for Image Classification","created":"2020-08-04","cited_by_count":50},{"id":"2112.04731","title":"Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning","created":"2021-12-09","cited_by_count":49},{"id":"2212.04842","title":"PIVOT: Prompting for Video Continual Learning","created":"2022-12-09","cited_by_count":45},{"id":"2211.15969","title":"Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference","created":"2022-11-29","cited_by_count":44},{"id":"2207.08605","title":"Class-incremental Novel Class Discovery","created":"2022-07-18","cited_by_count":42},{"id":"2203.16102","title":"Continual Normalization: Rethinking Batch Normalization for Online Continual Learning","created":"2022-03-30","cited_by_count":40},{"id":"2112.01882","title":"Incremental Learning in Semantic Segmentation from Image Labels","created":"2021-12-03","cited_by_count":39}],"next_cursor":"100"}