{"list":"other","total":56,"rows":[{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"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":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"2002.08546","title":"Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation","created":"2020-02-20","cited_by_count":848},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2005.04966","title":"Prototypical Contrastive Learning of Unsupervised Representations","created":"2020-05-11","cited_by_count":640},{"id":"1811.12833","title":"ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation","created":"2018-11-30","cited_by_count":623},{"id":"1605.06636","title":"Deep Transfer Learning with Joint Adaptation Networks","created":"2016-05-21","cited_by_count":612},{"id":"1412.3474","title":"Deep Domain Confusion: Maximizing for Domain Invariance","created":"2014-12-10","cited_by_count":600},{"id":"1911.05371","title":"Self-labelling via simultaneous clustering and representation learning","created":"2019-11-13","cited_by_count":528},{"id":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"id":"1901.00976","title":"Contrastive Adaptation Network for Unsupervised Domain Adaptation","created":"2019-01-04","cited_by_count":407},{"id":"1904.06487","title":"Semi-supervised Domain Adaptation via Minimax Entropy","created":"2019-04-13","cited_by_count":335},{"id":"2010.15980","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","created":"2020-10-29","cited_by_count":249},{"id":"2004.04393","title":"Universal Source-Free Domain Adaptation","created":"2020-04-09","cited_by_count":220},{"id":"2202.10936","title":"A Survey of Vision-Language Pre-Trained Models","created":"2022-02-18","cited_by_count":177},{"id":"2002.07953","title":"Universal Domain Adaptation through Self Supervision","created":"2020-02-19","cited_by_count":172},{"id":"1904.11227","title":"Transferrable Prototypical Networks for Unsupervised Domain Adaptation","created":"2019-04-25","cited_by_count":141},{"id":"2204.03649","title":"Unsupervised Prompt Learning for Vision-Language Models","created":"2022-04-07","cited_by_count":127},{"id":"2102.09003","title":"Domain Impression: A Source Data Free Domain Adaptation Method","created":"2021-02-17","cited_by_count":91},{"id":"1707.07901","title":"Partial Transfer Learning with Selective Adversarial Networks","created":"2017-07-25","cited_by_count":85},{"id":"2103.16765","title":"Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation","created":"2021-03-31","cited_by_count":83},{"id":"1711.10288","title":"Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation","created":"2017-11-28","cited_by_count":71},{"id":"2112.01573","title":"FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization","created":"2021-12-02","cited_by_count":71},{"id":"2110.12024","title":"A Prototype-Oriented Framework for Unsupervised Domain Adaptation","created":"2021-10-22","cited_by_count":62},{"id":"2201.05867","title":"Transferability in Deep Learning: A Survey","created":"2022-01-15","cited_by_count":57},{"id":"2207.09239","title":"Assaying Out-Of-Distribution Generalization in Transfer Learning","created":"2022-07-19","cited_by_count":53},{"id":"2010.10604","title":"Bayesian Attention Modules","created":"2020-10-20","cited_by_count":51},{"id":"2008.01389","title":"Class-Incremental Domain Adaptation","created":"2020-08-04","cited_by_count":36},{"id":"2203.01570","title":"Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings","created":"2022-03-03","cited_by_count":36},{"id":"2109.04408","title":"Learning with Different Amounts of Annotation: From Zero to Many Labels","created":"2021-09-09","cited_by_count":28},{"id":"2106.05251","title":"Bayesian Attention Belief Networks","created":"2021-06-09","cited_by_count":25},{"id":"2205.04980","title":"ALLSH: Active Learning Guided by Local Sensitivity and Hardness","created":"2022-05-10","cited_by_count":23},{"id":"2012.14100","title":"Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions","created":"2020-12-28","cited_by_count":22},{"id":"2110.09140","title":"Learning Prototype-oriented Set Representations for Meta-Learning","created":"2021-10-18","cited_by_count":19},{"id":"2110.12567","title":"Alignment Attention by Matching Key and Query Distributions","created":"2021-10-25","cited_by_count":14},{"id":"2002.01690","title":"Entropy Minimization vs. Diversity Maximization for Domain Adaptation","created":"2020-02-05","cited_by_count":8},{"id":"2102.06859","title":"Capturing Label Distribution: A Case Study in NLI","created":"2021-02-13","cited_by_count":6},{"id":"2302.03807","title":"A Prototype-Oriented Clustering for Domain Shift with Source Privacy","created":"2023-02-08","cited_by_count":2}],"next_cursor":null}