{"list":"other","total":64,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1809.10341","title":"Deep Graph Infomax","created":"2018-09-27","cited_by_count":1106},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"1712.02560","title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","created":"2017-12-07","cited_by_count":683},{"id":"1310.1531","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","created":"2013-10-06","cited_by_count":424},{"id":"2207.09519","title":"Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification","created":"2022-07-19","cited_by_count":362},{"id":"1904.06487","title":"Semi-supervised Domain Adaptation via Minimax Entropy","created":"2019-04-13","cited_by_count":335},{"id":"1904.05801","title":"Bridging Theory and Algorithm for Domain Adaptation","created":"2019-04-11","cited_by_count":332},{"id":"1711.04043","title":"Few-Shot Learning with Graph Neural Networks","created":"2017-11-10","cited_by_count":324},{"id":"2101.06329","title":"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning","created":"2021-01-15","cited_by_count":301},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273},{"id":"1911.03437","title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","created":"2019-11-08","cited_by_count":254},{"id":"2205.03340","title":"Prompt Distribution Learning","created":"2022-05-06","cited_by_count":235},{"id":"1802.01483","title":"Explicit Inductive Bias for Transfer Learning with Convolutional Networks","created":"2018-02-05","cited_by_count":227},{"id":"2106.05095","title":"ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation","created":"2021-06-09","cited_by_count":184},{"id":"2010.03622","title":"Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data","created":"2020-10-07","cited_by_count":180},{"id":"2303.02151","title":"Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners","created":"2023-03-03","cited_by_count":152},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148},{"id":"2204.08790","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","created":"2022-04-19","cited_by_count":141},{"id":"1703.04826","title":"Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling","created":"2017-03-14","cited_by_count":137},{"id":"2112.01522","title":"Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks","created":"2021-12-02","cited_by_count":125},{"id":"2106.04732","title":"AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation","created":"2021-06-08","cited_by_count":104},{"id":"2208.07204","title":"USB: A Unified Semi-supervised Learning Benchmark for Classification","created":"2022-08-12","cited_by_count":95},{"id":"1704.06803","title":"Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks","created":"2017-04-22","cited_by_count":88},{"id":"1901.09229","title":"DELTA: DEep Learning Transfer using Feature Map with Attention for Convolutional Networks","created":"2019-01-26","cited_by_count":80},{"id":"2204.09222","title":"K-LITE: Learning Transferable Visual Models with External Knowledge","created":"2022-04-20","cited_by_count":79},{"id":"2203.11819","title":"A Broad Study of Pre-training for Domain Generalization and Adaptation","created":"2022-03-22","cited_by_count":65},{"id":"2202.07136","title":"Debiased Self-Training for Semi-Supervised Learning","created":"2022-02-15","cited_by_count":62},{"id":"2103.12562","title":"Transferable Semantic Augmentation for Domain Adaptation","created":"2021-03-23","cited_by_count":56},{"id":"2102.12903","title":"Self-Tuning for Data-Efficient Deep Learning","created":"2021-02-25","cited_by_count":39},{"id":"2111.12292","title":"Improved Fine-Tuning by Better Leveraging Pre-Training Data","created":"2021-11-24","cited_by_count":36},{"id":"2210.08901","title":"Contrastive Language-Image Pre-Training with Knowledge Graphs","created":"2022-10-17","cited_by_count":34},{"id":"2302.05738","title":"Cross-Modal Fine-Tuning: Align then Refine","created":"2023-02-11","cited_by_count":34},{"id":"2112.09690","title":"Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition","created":"2021-12-17","cited_by_count":29},{"id":"2003.00197","title":"VideoSSL: Semi-Supervised Learning for Video Classification","created":"2020-02-29","cited_by_count":27},{"id":"2004.06272","title":"Bidirectional Graph Reasoning Network for Panoptic Segmentation","created":"2020-04-14","cited_by_count":26}],"next_cursor":null}