{"list":"other","total":124,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1711.03213","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","created":"2017-11-08","cited_by_count":1082},{"id":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"1811.12833","title":"ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation","created":"2018-11-30","cited_by_count":623},{"id":"1802.10501","title":"Predictive Uncertainty Estimation via Prior Networks","created":"2018-02-28","cited_by_count":557},{"id":"1707.00600","title":"Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly","created":"2017-07-03","cited_by_count":538},{"id":"1803.04189","title":"Noise2Noise: Learning Image Restoration without Clean Data","created":"2018-03-12","cited_by_count":533},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"2207.08051","title":"SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery","created":"2022-07-17","cited_by_count":408},{"id":"1812.02849","title":"A Survey of Unsupervised Deep Domain Adaptation","created":"2018-12-06","cited_by_count":361},{"id":"1902.06326","title":"PIXOR: Real-time 3D Object Detection from Point Clouds","created":"2019-02-17","cited_by_count":358},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"1909.00133","title":"Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark","created":"2019-08-31","cited_by_count":340},{"id":"1905.03677","title":"Learning Loss for Active Learning","created":"2019-05-09","cited_by_count":336},{"id":"2211.06220","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","created":"2022-11-10","cited_by_count":328},{"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":"1904.00370","title":"Variational Adversarial Active Learning","created":"2019-03-31","cited_by_count":284},{"id":"1906.05433","title":"Tackling Climate Change with Machine Learning","created":"2019-06-10","cited_by_count":265},{"id":"1904.05044","title":"Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations","created":"2019-04-10","cited_by_count":247},{"id":"1908.06948","title":"Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography","created":"2019-08-16","cited_by_count":244},{"id":"1301.3666","title":"Zero-Shot Learning Through Cross-Modal Transfer","created":"2013-01-16","cited_by_count":237},{"id":"2011.09980","title":"Geography-Aware Self-Supervised Learning","created":"2020-11-19","cited_by_count":190},{"id":"1910.04851","title":"Addressing Failure Prediction by Learning Model Confidence","created":"2019-10-01","cited_by_count":186},{"id":"2104.12225","title":"DC3: A learning method for optimization with hard constraints","created":"2021-04-25","cited_by_count":184},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172},{"id":"2107.07933","title":"Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks","created":"2021-07-16","cited_by_count":143},{"id":"1911.12676","title":"xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation","created":"2019-11-28","cited_by_count":129},{"id":"1702.05374","title":"Domain Adaptation for Visual Applications: A Comprehensive Survey","created":"2017-02-17","cited_by_count":128},{"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":"2306.03831","title":"GEO-Bench: Toward Foundation Models for Earth Monitoring","created":"2023-06-06","cited_by_count":124},{"id":"2304.14065","title":"Lightweight, Pre-trained Transformers for Remote Sensing Timeseries","created":"2023-04-27","cited_by_count":103},{"id":"1911.11789","title":"ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation","created":"2019-11-26","cited_by_count":96},{"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":"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":"2204.08322","title":"A high-resolution canopy height model of the Earth","created":"2022-04-13","cited_by_count":91},{"id":"2304.06798","title":"On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence","created":"2023-04-13","cited_by_count":88},{"id":"2110.04770","title":"Weakly Supervised Contrastive Learning","created":"2021-10-10","cited_by_count":81},{"id":"1603.06201","title":"A Survey on Object Detection in Optical Remote Sensing Images","created":"2016-03-20","cited_by_count":78},{"id":"2005.01463","title":"MeshfreeFlowNet: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Framework","created":"2020-05-01","cited_by_count":78},{"id":"1509.04767","title":"Zero-Shot Learning via Semantic Similarity Embedding","created":"2015-09-15","cited_by_count":74},{"id":"2005.01094","title":"Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities","created":"2020-05-03","cited_by_count":71},{"id":"2112.10646","title":"Raw High-Definition Radar for Multi-Task Learning","created":"2021-12-20","cited_by_count":69},{"id":"2305.01118","title":"CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations","created":"2023-05-01","cited_by_count":69},{"id":"2005.01456","title":"CARRADA Dataset: Camera and Automotive Radar with Range-Angle-Doppler Annotations","created":"2020-05-04","cited_by_count":60},{"id":"2211.09808","title":"Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks","created":"2022-11-17","cited_by_count":57},{"id":"2301.04944","title":"ViTs for SITS: Vision Transformers for Satellite Image Time Series","created":"2023-01-12","cited_by_count":56},{"id":"2112.07558","title":"Multi-Modal Temporal Attention Models for Crop Mapping from Satellite Time Series","created":"2021-12-14","cited_by_count":49},{"id":"1707.09472","title":"Weakly-supervised learning of visual relations","created":"2017-07-29","cited_by_count":36},{"id":"2004.13390","title":"Meta-Learning for Few-Shot Land Cover Classification","created":"2020-04-28","cited_by_count":34},{"id":"2103.16214","title":"Multi-View Radar Semantic Segmentation","created":"2021-03-30","cited_by_count":34},{"id":"2011.05479","title":"ForestNet: Classifying Drivers of Deforestation in Indonesia using Deep Learning on Satellite Imagery","created":"2020-11-11","cited_by_count":27},{"id":"2104.07784","title":"A survey of active learning algorithms for supervised remote sensing image classification","created":"2021-04-15","cited_by_count":27},{"id":"2103.03975","title":"Global canopy height regression and uncertainty estimation from GEDI LIDAR waveforms with deep ensembles","created":"2021-03-05","cited_by_count":26},{"id":"2211.08129","title":"Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works","created":"2022-11-15","cited_by_count":24},{"id":"2006.07826","title":"Few-shot Object Detection on Remote Sensing Images","created":"2020-06-14","cited_by_count":23},{"id":"2306.06842","title":"AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation","created":"2023-06-12","cited_by_count":23},{"id":"2101.03409","title":"Active Fire Detection in Landsat-8 Imagery: a Large-Scale Dataset and a Deep-Learning Study","created":"2021-01-09","cited_by_count":21},{"id":"2110.13148","title":"As if by magic: self-supervised training of deep despeckling networks with MERLIN","created":"2021-10-25","cited_by_count":18}],"next_cursor":"100"}