{"list":"other","total":79,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"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":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"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":"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":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"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":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1607.01759","title":"Bag of Tricks for Efficient Text Classification","created":"2016-07-06","cited_by_count":876},{"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":"1312.6211","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","created":"2013-12-21","cited_by_count":722},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2204.04799","title":"DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning","created":"2022-04-10","cited_by_count":642},{"id":"1904.07734","title":"Three scenarios for continual learning","created":"2019-04-15","cited_by_count":614},{"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":"1911.00359","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","created":"2019-11-01","cited_by_count":548},{"id":"1805.06370","title":"Progress & Compress: A scalable framework for continual learning","created":"2018-05-16","cited_by_count":520},{"id":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"1910.07104","title":"Orthogonal Gradient Descent for Continual Learning","created":"2019-10-15","cited_by_count":369},{"id":"1711.07846","title":"Functional Map of the World","created":"2017-11-21","cited_by_count":338},{"id":"1705.03550","title":"CORe50: a New Dataset and Benchmark for Continuous Object Recognition","created":"2017-05-09","cited_by_count":289},{"id":"1703.08475","title":"Overcoming Catastrophic Forgetting by Incremental Moment Matching","created":"2017-03-24","cited_by_count":243},{"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":"2002.00718","title":"Modeling the Background for Incremental Learning in Semantic Segmentation","created":"2020-02-03","cited_by_count":190},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190},{"id":"2006.06958","title":"Understanding the Role of Training Regimes in Continual Learning","created":"2020-06-12","cited_by_count":180},{"id":"2111.11431","title":"RedCaps: web-curated image-text data created by the people, for the people","created":"2021-11-22","cited_by_count":180},{"id":"2305.03053","title":"ZipIt! Merging Models from Different Tasks without Training","created":"2023-05-04","cited_by_count":179},{"id":"2110.03215","title":"Towards Continual Knowledge Learning of Language Models","created":"2021-10-07","cited_by_count":174},{"id":"1907.13372","title":"Incremental Learning Techniques for Semantic Segmentation","created":"2019-07-31","cited_by_count":141},{"id":"1809.05922","title":"Memory Efficient Experience Replay for Streaming Learning","created":"2018-09-16","cited_by_count":128},{"id":"2205.11388","title":"StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models","created":"2022-05-23","cited_by_count":126},{"id":"2204.14211","title":"TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models","created":"2022-04-29","cited_by_count":119},{"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":"2303.06628","title":"Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models","created":"2023-03-12","cited_by_count":112},{"id":"2201.06289","title":"The CLEAR Benchmark: Continual LEArning on Real-World Imagery","created":"2022-01-17","cited_by_count":93},{"id":"2012.12631","title":"Efficient Continual Learning with Modular Networks and Task-Driven Priors","created":"2020-12-23","cited_by_count":88},{"id":"2112.12533","title":"PyCIL: A Python Toolbox for Class-Incremental Learning","created":"2021-12-23","cited_by_count":83},{"id":"2305.19270","title":"Learning without Forgetting for Vision-Language Models","created":"2023-05-30","cited_by_count":79},{"id":"2108.09020","title":"Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data","created":"2021-08-20","cited_by_count":69},{"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":"2207.09248","title":"Don't Stop Learning: Towards Continual Learning for the CLIP Model","created":"2022-07-19","cited_by_count":61},{"id":"2303.11165","title":"Computationally Budgeted Continual Learning: What Does Matter?","created":"2023-03-20","cited_by_count":61},{"id":"2305.07437","title":"Continual Vision-Language Representation Learning with Off-Diagonal Information","created":"2023-05-11","cited_by_count":40},{"id":"2210.03482","title":"CLAD: A realistic Continual Learning benchmark for Autonomous Driving","created":"2022-10-07","cited_by_count":36},{"id":"2108.11005","title":"Wanderlust: Online Continual Object Detection in the Real World","created":"2021-08-25","cited_by_count":34},{"id":"2009.09929","title":"CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions","created":"2020-09-14","cited_by_count":26},{"id":"2010.02418","title":"The Effectiveness of Memory Replay in Large Scale Continual Learning","created":"2020-10-06","cited_by_count":26},{"id":"2004.11545","title":"Dropout as an Implicit Gating Mechanism For Continual Learning","created":"2020-04-24","cited_by_count":24},{"id":"2112.02925","title":"Is Class-Incremental Enough for Continual Learning?","created":"2021-12-06","cited_by_count":22},{"id":"2207.12576","title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","created":"2022-07-25","cited_by_count":20},{"id":"2211.11747","title":"NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research","created":"2022-11-15","cited_by_count":18},{"id":"2111.01956","title":"One Pass ImageNet","created":"2021-11-03","cited_by_count":11},{"id":"2306.15769","title":"What Makes ImageNet Look Unlike LAION","created":"2023-06-27","cited_by_count":9},{"id":"2303.06480","title":"Knowledge Distillation for Efficient Sequences of Training Runs","created":"2023-03-11","cited_by_count":3}],"next_cursor":null}