{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"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":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2011.09157","title":"Dense Contrastive Learning for Self-Supervised Visual Pre-Training","created":"2020-11-18","cited_by_count":512},{"id":"2207.08051","title":"SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery","created":"2022-07-17","cited_by_count":408},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"2010.01028","title":"Hard Negative Mixing for Contrastive Learning","created":"2020-10-02","cited_by_count":402},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"id":"2212.14532","title":"Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning","created":"2022-12-30","cited_by_count":308},{"id":"1906.05433","title":"Tackling Climate Change with Machine Learning","created":"2019-06-10","cited_by_count":265},{"id":"2111.08276","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","created":"2021-11-16","cited_by_count":256},{"id":"2008.05659","title":"What Should Not Be Contrastive in Contrastive Learning","created":"2020-08-13","cited_by_count":226},{"id":"2103.16607","title":"Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data","created":"2021-03-30","cited_by_count":215},{"id":"2202.10401","title":"Vision-Language Pre-Training with Triple Contrastive Learning","created":"2022-02-21","cited_by_count":212},{"id":"2107.14222","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","created":"2021-07-29","cited_by_count":207},{"id":"2011.09980","title":"Geography-Aware Self-Supervised Learning","created":"2020-11-19","cited_by_count":190},{"id":"2012.02951","title":"FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding","created":"2020-12-05","cited_by_count":181},{"id":"2210.07839","title":"Contrastive Audio-Visual Masked Autoencoder","created":"2022-10-02","cited_by_count":146},{"id":"1710.03959","title":"Deep learning in remote sensing: a review","created":"2017-10-11","cited_by_count":128},{"id":"2210.01571","title":"VICRegL: Self-Supervised Learning of Local Visual Features","created":"2022-10-04","cited_by_count":118},{"id":"1805.02855","title":"Tile2Vec: Unsupervised representation learning for spatially distributed data","created":"2018-05-08","cited_by_count":110},{"id":"2212.07525","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","created":"2022-12-14","cited_by_count":110},{"id":"2110.02095","title":"Exploring the Limits of Large Scale Pre-training","created":"2021-10-05","cited_by_count":104},{"id":"2305.00729","title":"What Do Self-Supervised Vision Transformers Learn?","created":"2023-05-01","cited_by_count":93},{"id":"2105.07921","title":"BigEarthNet-MM: A Large Scale Multi-Modal Multi-Label Benchmark Archive for Remote Sensing Image Classification and Retrieval","created":"2021-05-17","cited_by_count":92},{"id":"2211.07044","title":"SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth Observation","created":"2022-11-13","cited_by_count":84},{"id":"2103.12718","title":"Self-Supervised Pretraining Improves Self-Supervised Pretraining","created":"2021-03-23","cited_by_count":82},{"id":"2305.01118","title":"CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations","created":"2023-05-01","cited_by_count":69},{"id":"2303.13496","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","created":"2023-03-23","cited_by_count":68},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59},{"id":"2104.07070","title":"Self-Supervised Learning of Remote Sensing Scene Representations Using Contrastive Multiview Coding","created":"2021-04-14","cited_by_count":58},{"id":"2112.02447","title":"Next Day Wildfire Spread: A Machine Learning Data Set to Predict Wildfire Spreading from Remote-Sensing Data","created":"2021-12-04","cited_by_count":42},{"id":"1510.00098","title":"Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping","created":"2015-10-01","cited_by_count":37},{"id":"2103.14005","title":"Contrasting Contrastive Self-Supervised Representation Learning Pipelines","created":"2021-03-25","cited_by_count":37},{"id":"2010.00882","title":"Remote Sensing Image Scene Classification with Self-Supervised Paradigm under Limited Labeled Samples","created":"2020-10-02","cited_by_count":36},{"id":"2309.05300","title":"Decoupling Common and Unique Representations for Multimodal Self-supervised Learning","created":"2023-09-11","cited_by_count":36},{"id":"2006.12119","title":"The color out of space: learning self-supervised representations for Earth Observation imagery","created":"2020-06-22","cited_by_count":34},{"id":"2106.10605","title":"Global and Local Contrastive Self-Supervised Learning for Semantic Segmentation of HR Remote Sensing Images","created":"2021-06-20","cited_by_count":31},{"id":"1912.02783","title":"Self-Supervised Learning of Video-Induced Visual Invariances","created":"2019-12-05","cited_by_count":29},{"id":"2303.16839","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","created":"2023-03-29","cited_by_count":24},{"id":"2112.00570","title":"Toward Foundation Models for Earth Monitoring: Proposal for a Climate Change Benchmark","created":"2021-12-01","cited_by_count":22},{"id":"2206.08347","title":"Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning","created":"2022-06-16","cited_by_count":20},{"id":"2303.06670","title":"Extending global-local view alignment for self-supervised learning with remote sensing imagery","created":"2023-03-12","cited_by_count":20},{"id":"2209.02329","title":"Multimodal contrastive learning for remote sensing tasks","created":"2022-09-06","cited_by_count":18},{"id":"2304.10520","title":"Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget","created":"2023-04-20","cited_by_count":15},{"id":"2006.16866","title":"Rapid Response Crop Maps in Data Sparse Regions","created":"2020-06-23","cited_by_count":14},{"id":"2109.00120","title":"Contrastive Multiview Coding with Electro-optics for SAR Semantic Segmentation","created":"2021-08-31","cited_by_count":14},{"id":"1902.01449","title":"Generalization Bounds For Unsupervised and Semi-Supervised Learning With Autoencoders","created":"2019-02-04","cited_by_count":11},{"id":"2208.09374","title":"VLMAE: Vision-Language Masked Autoencoder","created":"2022-08-19","cited_by_count":11},{"id":"2303.13455","title":"CoBIT: A Contrastive Bi-directional Image-Text Generation Model","created":"2023-03-23","cited_by_count":11},{"id":"2202.11429","title":"A Novel Self-Supervised Cross-Modal Image Retrieval Method In Remote Sensing","created":"2022-02-23","cited_by_count":10},{"id":"2209.14969","title":"Transfer Learning with Pretrained Remote Sensing Transformers","created":"2022-09-28","cited_by_count":6},{"id":"2202.13251","title":"Supervising Remote Sensing Change Detection Models with 3D Surface Semantics","created":"2022-02-26","cited_by_count":4},{"id":"2102.06260","title":"Towards DeepSentinel: An extensible corpus of labelled Sentinel-1 and -2 imagery and a general-purpose sensor-fusion semantic embedding model","created":"2021-02-11","cited_by_count":2}],"next_cursor":null}