{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"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":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"1912.01991","title":"Self-Supervised Learning of Pretext-Invariant Representations","created":"2019-12-04","cited_by_count":808},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"2012.07177","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","created":"2020-12-13","cited_by_count":596},{"id":"1911.05371","title":"Self-labelling via simultaneous clustering and representation learning","created":"2019-11-13","cited_by_count":528},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"2109.07547","title":"RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching","created":"2021-09-15","cited_by_count":353},{"id":"1804.06516","title":"Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization","created":"2018-04-18","cited_by_count":294},{"id":"2008.08465","title":"CosyPose: Consistent multi-view multi-object 6D pose estimation","created":"2020-08-19","cited_by_count":287},{"id":"2003.06957","title":"Frustratingly Simple Few-Shot Object Detection","created":"2020-03-16","cited_by_count":282},{"id":"1901.09005","title":"Revisiting Self-Supervised Visual Representation Learning","created":"2019-01-25","cited_by_count":251},{"id":"1904.06587","title":"GA-Net: Guided Aggregation Net for End-to-end Stereo Matching","created":"2019-04-13","cited_by_count":244},{"id":"1904.03436","title":"Unsupervised Embedding Learning via Invariant and Spreading Instance Feature","created":"2019-04-06","cited_by_count":232},{"id":"2102.04803","title":"DetCo: Unsupervised Contrastive Learning for Object Detection","created":"2021-02-09","cited_by_count":205},{"id":"1708.07860","title":"Multi-task Self-Supervised Visual Learning","created":"2017-08-25","cited_by_count":200},{"id":"1610.01983","title":"Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?","created":"2016-10-06","cited_by_count":194},{"id":"2103.10957","title":"Efficient Visual Pretraining with Contrastive Detection","created":"2021-03-19","cited_by_count":150},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130},{"id":"1911.13287","title":"Domain-invariant Stereo Matching Networks","created":"2019-11-29","cited_by_count":109},{"id":"2102.08318","title":"Instance Localization for Self-supervised Detection Pretraining","created":"2021-02-16","cited_by_count":99},{"id":"2103.12902","title":"Region Similarity Representation Learning","created":"2021-03-24","cited_by_count":96},{"id":"1804.06534","title":"Falling Things: A Synthetic Dataset for 3D Object Detection and Pose Estimation","created":"2018-04-18","cited_by_count":92},{"id":"1904.11567","title":"Unsupervised Deep Learning by Neighbourhood Discovery","created":"2019-04-25","cited_by_count":78},{"id":"2101.08482","title":"Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning","created":"2021-01-21","cited_by_count":78},{"id":"1911.01911","title":"BlenderProc","created":"2019-10-25","cited_by_count":77},{"id":"2106.04550","title":"DETReg: Unsupervised Pretraining with Region Priors for Object Detection","created":"2021-06-08","cited_by_count":76},{"id":"2103.06122","title":"Spatially Consistent Representation Learning","created":"2021-03-10","cited_by_count":64},{"id":"1710.10710","title":"On Pre-Trained Image Features and Synthetic Images for Deep Learning","created":"2017-10-29","cited_by_count":51},{"id":"2006.14618","title":"Parametric Instance Classification for Unsupervised Visual Feature Learning","created":"2020-06-25","cited_by_count":41},{"id":"1608.01745","title":"Play and Learn: Using Video Games to Train Computer Vision Models","created":"2016-08-05","cited_by_count":16},{"id":"1803.04610","title":"Target Driven Instance Detection","created":"2018-03-13","cited_by_count":14},{"id":"2011.14488","title":"Self-Supervised Real-to-Sim Scene Generation","created":"2020-11-30","cited_by_count":13}],"next_cursor":null}