{"list":"other","total":156,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"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":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"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":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1609.04802","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","created":"2016-09-15","cited_by_count":1908},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"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":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"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":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"1511.06335","title":"Unsupervised Deep Embedding for Clustering Analysis","created":"2015-11-19","cited_by_count":767},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"1902.06162","title":"Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey","created":"2019-02-16","cited_by_count":657},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2010.00747","title":"Contrastive Learning of Medical Visual Representations from Paired Images and Text","created":"2020-10-02","cited_by_count":641},{"id":"2005.04966","title":"Prototypical Contrastive Learning of Unsupervised Representations","created":"2020-05-11","cited_by_count":640},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"id":"1910.01279","title":"Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks","created":"2019-10-03","cited_by_count":582},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2011.00362","title":"A Survey on Contrastive Self-supervised Learning","created":"2020-10-31","cited_by_count":554},{"id":"1911.05371","title":"Self-labelling via simultaneous clustering and representation learning","created":"2019-11-13","cited_by_count":528},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"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":"2010.01028","title":"Hard Negative Mixing for Contrastive Learning","created":"2020-10-02","cited_by_count":402},{"id":"2005.12320","title":"SCAN: Learning to Classify Images without Labels","created":"2020-05-25","cited_by_count":352},{"id":"1608.05167","title":"AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification","created":"2016-08-18","cited_by_count":347},{"id":"1711.07846","title":"Functional Map of the World","created":"2017-11-21","cited_by_count":338},{"id":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297},{"id":"1805.06561","title":"DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images","created":"2018-05-17","cited_by_count":277},{"id":"2009.09687","title":"Contrastive Clustering","created":"2020-09-21","cited_by_count":265},{"id":"1605.07157","title":"Unsupervised Learning for Physical Interaction through Video Prediction","created":"2016-05-23","cited_by_count":260},{"id":"2102.06810","title":"Understanding self-supervised Learning Dynamics without Contrastive Pairs","created":"2021-02-12","cited_by_count":256},{"id":"1603.06668","title":"Learning Representations for Automatic Colorization","created":"2016-03-22","cited_by_count":251},{"id":"1901.09005","title":"Revisiting Self-Supervised Visual Representation Learning","created":"2019-01-25","cited_by_count":251},{"id":"2012.15409","title":"UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning","created":"2020-12-31","cited_by_count":239},{"id":"1902.06148","title":"BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding","created":"2019-02-16","cited_by_count":234},{"id":"1611.09842","title":"Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction","created":"2016-11-29","cited_by_count":217},{"id":"2103.16607","title":"Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data","created":"2021-03-30","cited_by_count":215},{"id":"1604.03628","title":"Joint Unsupervised Learning of Deep Representations and Image Clusters","created":"2016-04-13","cited_by_count":205},{"id":"1903.12355","title":"Local Aggregation for Unsupervised Learning of Visual Embeddings","created":"2019-03-29","cited_by_count":204},{"id":"2102.12219","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","created":"2021-02-24","cited_by_count":204},{"id":"1905.01235","title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","created":"2019-05-03","cited_by_count":201},{"id":"2103.01988","title":"Self-supervised Pretraining of Visual Features in the Wild","created":"2021-03-02","cited_by_count":198},{"id":"2011.09980","title":"Geography-Aware Self-Supervised Learning","created":"2020-11-19","cited_by_count":190},{"id":"1703.04044","title":"Colorization as a Proxy Task for Visual Understanding","created":"2017-03-11","cited_by_count":175},{"id":"1706.08033","title":"Decomposing Motion and Content for Natural Video Sequence Prediction","created":"2017-06-25","cited_by_count":169},{"id":"2106.04538","title":"What Makes Multi-modal Learning Better than Single (Provably)","created":"2021-06-08","cited_by_count":153},{"id":"2110.09327","title":"Self-Supervised Representation Learning: Introduction, Advances and Challenges","created":"2021-10-18","cited_by_count":148},{"id":"2206.13188","title":"Self-supervised Learning in Remote Sensing: A Review","created":"2022-06-27","cited_by_count":137},{"id":"1710.03959","title":"Deep learning in remote sensing: a review","created":"2017-10-11","cited_by_count":128},{"id":"2110.05025","title":"Self-supervised Learning is More Robust to Dataset Imbalance","created":"2021-10-11","cited_by_count":123},{"id":"1805.02855","title":"Tile2Vec: Unsupervised representation learning for spatially distributed data","created":"2018-05-08","cited_by_count":110},{"id":"2204.02825","title":"An Empirical Study of Remote Sensing Pretraining","created":"2022-04-06","cited_by_count":105},{"id":"2205.03892","title":"ConvMAE: Masked Convolution Meets Masked Autoencoders","created":"2022-05-08","cited_by_count":105},{"id":"2111.00743","title":"Towards the Generalization of Contrastive Self-Supervised Learning","created":"2021-11-01","cited_by_count":99},{"id":"1906.07789","title":"SEN12MS -- A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusion","created":"2019-06-18","cited_by_count":95},{"id":"1811.11212","title":"Self-Supervised GANs via Auxiliary Rotation Loss","created":"2018-11-27","cited_by_count":94},{"id":"1805.00385","title":"Boosting Self-Supervised Learning via Knowledge Transfer","created":"2018-05-01","cited_by_count":92},{"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":"2105.03761","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","created":"2021-05-08","cited_by_count":84},{"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}],"next_cursor":"100"}