{"list":"other","total":57,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"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":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"2008.02268","title":"NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections","created":"2020-08-05","cited_by_count":1232},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"2008.00951","title":"Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation","created":"2020-08-03","cited_by_count":727},{"id":"2102.13090","title":"IBRNet: Learning Multi-View Image-Based Rendering","created":"2021-02-25","cited_by_count":703},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"1508.06576","title":"A Neural Algorithm of Artistic Style","created":"2015-08-26","cited_by_count":483},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"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":"1912.08804","title":"SynSin: End-to-end View Synthesis from a Single Image","created":"2019-12-18","cited_by_count":364},{"id":"1908.03826","title":"DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better","created":"2019-08-10","cited_by_count":362},{"id":"2006.06882","title":"Rethinking Pre-training and Self-training","created":"2020-06-11","cited_by_count":352},{"id":"1808.00948","title":"Diverse Image-to-Image Translation via Disentangled Representations","created":"2018-08-02","cited_by_count":296},{"id":"1906.08988","title":"A Fourier Perspective on Model Robustness in Computer Vision","created":"2019-06-21","cited_by_count":288},{"id":"2004.11364","title":"Single-View View Synthesis with Multiplane Images","created":"2020-04-23","cited_by_count":263},{"id":"1808.00449","title":"Learning Blind Video Temporal Consistency","created":"2018-08-01","cited_by_count":253},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249},{"id":"2012.09855","title":"Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image","created":"2020-12-17","cited_by_count":243},{"id":"2008.05511","title":"Free View Synthesis","created":"2020-08-12","cited_by_count":231},{"id":"1707.09405","title":"Photographic Image Synthesis with Cascaded Refinement Networks","created":"2017-07-28","cited_by_count":223},{"id":"1602.02644","title":"Generating Images with Perceptual Similarity Metrics based on Deep Networks","created":"2016-02-08","cited_by_count":222},{"id":"2103.10428","title":"Large Scale Image Completion via Co-Modulated Generative Adversarial Networks","created":"2021-03-18","cited_by_count":220},{"id":"1906.06423","title":"Fixing the train-test resolution discrepancy","created":"2019-06-14","cited_by_count":209},{"id":"2006.14200","title":"SRFlow: Learning the Super-Resolution Space with Normalizing Flow","created":"2020-06-25","cited_by_count":209},{"id":"1611.10012","title":"Speed/accuracy trade-offs for modern convolutional object detectors","created":"2016-11-30","cited_by_count":198},{"id":"2004.01860","title":"Deblurring by Realistic Blurring","created":"2020-04-04","cited_by_count":188},{"id":"1804.01523","title":"Stochastic Adversarial Video Prediction","created":"2018-04-04","cited_by_count":173},{"id":"1901.00212","title":"EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning","created":"2019-01-01","cited_by_count":163},{"id":"1701.01036","title":"Demystifying Neural Style Transfer","created":"2017-01-04","cited_by_count":152},{"id":"2002.09219","title":"Stochastic Latent Residual Video Prediction","created":"2020-02-21","cited_by_count":108},{"id":"2007.08558","title":"On Robustness and Transferability of Convolutional Neural Networks","created":"2020-07-16","cited_by_count":98},{"id":"2006.14536","title":"Smooth Adversarial Training","created":"2020-06-25","cited_by_count":89},{"id":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","cited_by_count":87},{"id":"2101.10997","title":"Deep Burst Super-Resolution","created":"2021-01-26","cited_by_count":83},{"id":"2103.04174","title":"Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction","created":"2021-03-06","cited_by_count":75},{"id":"2106.15831","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","created":"2021-06-30","cited_by_count":75},{"id":"2104.05623","title":"Rethinking and Improving the Robustness of Image Style Transfer","created":"2021-04-08","cited_by_count":48},{"id":"1909.11229","title":"Pretraining boosts out-of-domain robustness for pose estimation","created":"2019-09-24","cited_by_count":47},{"id":"1711.02846","title":"Intriguing Properties of Adversarial Examples","created":"2017-11-08","cited_by_count":20},{"id":"1907.07640","title":"Robustness properties of Facebook's ResNeXt WSL models","created":"2019-07-17","cited_by_count":17},{"id":"2010.06512","title":"Transforming Neural Network Visual Representations to Predict Human Judgments of Similarity","created":"2020-10-13","cited_by_count":16},{"id":"2002.02559","title":"Impact of ImageNet Model Selection on Domain Adaptation","created":"2020-02-06","cited_by_count":15}],"next_cursor":null}