{"list":"other","total":69,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"1912.01991","title":"Self-Supervised Learning of Pretext-Invariant Representations","created":"2019-12-04","cited_by_count":808},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"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":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"1911.11929","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","created":"2019-11-27","cited_by_count":381},{"id":"1907.07484","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","created":"2019-07-17","cited_by_count":336},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"1912.04488","title":"SOLO: Segmenting Objects by Locations","created":"2019-12-10","cited_by_count":289},{"id":"1903.00241","title":"Mask Scoring R-CNN","created":"2019-03-01","cited_by_count":266},{"id":"1904.00760","title":"Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet","created":"2019-03-20","cited_by_count":260},{"id":"1808.08750","title":"Generalisation in humans and deep neural networks","created":"2018-08-27","cited_by_count":237},{"id":"2012.05208","title":"On the Binding Problem in Artificial Neural Networks","created":"2020-12-09","cited_by_count":233},{"id":"2011.08036","title":"Scaled-YOLOv4: Scaling Cross Stage Partial Network","created":"2020-11-16","cited_by_count":211},{"id":"2106.07411","title":"Partial success in closing the gap between human and machine vision","created":"2021-06-14","cited_by_count":185},{"id":"2104.02610","title":"On the Robustness of Vision Transformers to Adversarial Examples","created":"2021-03-31","cited_by_count":167},{"id":"2008.10032","title":"Seesaw Loss for Long-Tailed Instance Segmentation","created":"2020-08-23","cited_by_count":146},{"id":"1908.05005","title":"Benchmarking the Robustness of Semantic Segmentation Models","created":"2019-08-14","cited_by_count":111},{"id":"2105.07197","title":"Are Convolutional Neural Networks or Transformers more like human vision?","created":"2021-05-15","cited_by_count":109},{"id":"2007.11978","title":"The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation","created":"2020-07-23","cited_by_count":108},{"id":"2103.12340","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","created":"2021-03-23","cited_by_count":104},{"id":"1912.06218","title":"YOLACT++: Better Real-time Instance Segmentation","created":"2019-12-03","cited_by_count":84},{"id":"2007.08921","title":"Boundary-preserving Mask R-CNN","created":"2020-07-17","cited_by_count":74},{"id":"1711.10370","title":"Learning to Segment Every Thing","created":"2017-11-28","cited_by_count":65},{"id":"2101.11604","title":"Shape or Texture: Understanding Discriminative Features in CNNs","created":"2021-01-27","cited_by_count":52},{"id":"2108.06747","title":"SOTR: Segmenting Objects with Transformers","created":"2021-08-15","cited_by_count":42},{"id":"2107.02170","title":"On Model Calibration for Long-Tailed Object Detection and Instance Segmentation","created":"2021-07-05","cited_by_count":39},{"id":"2104.06402","title":"DropLoss for Long-Tail Instance Segmentation","created":"2021-04-13","cited_by_count":32},{"id":"2104.09789","title":"Does enhanced shape bias improve neural network robustness to common corruptions?","created":"2021-04-20","cited_by_count":32},{"id":"2106.03805","title":"3DB: A Framework for Debugging Computer Vision Models","created":"2021-06-07","cited_by_count":31},{"id":"2010.08377","title":"On the surprising similarities between supervised and self-supervised models","created":"2020-10-16","cited_by_count":29},{"id":"2104.05702","title":"Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection","created":"2021-04-12","cited_by_count":27},{"id":"1805.04025","title":"Deep Nets: What have they ever done for Vision?","created":"2018-05-10","cited_by_count":23},{"id":"2103.17220","title":"Scale-aware Automatic Augmentation for Object Detection","created":"2021-03-31","cited_by_count":23},{"id":"2007.12387","title":"Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation","created":"2020-07-24","cited_by_count":14},{"id":"2203.13312","title":"SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation","created":"2022-03-24","cited_by_count":12},{"id":"2104.04191","title":"SI-Score: An image dataset for fine-grained analysis of robustness to object location, rotation and size","created":"2021-04-09","cited_by_count":7},{"id":"2111.04204","title":"Natural Adversarial Objects","created":"2021-11-07","cited_by_count":7},{"id":"2106.13933","title":"Inverting and Understanding Object Detectors","created":"2021-06-26","cited_by_count":2}],"next_cursor":null}