{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"2003.10580","title":"Meta Pseudo Labels","created":"2020-03-23","cited_by_count":374},{"id":"1904.09925","title":"Attention Augmented Convolutional Networks","created":"2019-04-22","cited_by_count":363},{"id":"1907.08610","title":"Lookahead Optimizer: k steps forward, 1 step back","created":"2019-07-19","cited_by_count":336},{"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":"2104.05704","title":"Escaping the Big Data Paradigm with Compact Transformers","created":"2021-04-12","cited_by_count":264},{"id":"1810.12890","title":"DropBlock: A regularization method for convolutional networks","created":"2018-10-30","cited_by_count":262},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260},{"id":"2103.11816","title":"Incorporating Convolution Designs into Visual Transformers","created":"2021-03-22","cited_by_count":248},{"id":"2112.13492","title":"Vision Transformer for Small-Size Datasets","created":"2021-12-27","cited_by_count":122},{"id":"2003.13630","title":"TResNet: High Performance GPU-Dedicated Architecture","created":"2020-03-30","cited_by_count":119},{"id":"2106.03746","title":"Efficient Training of Visual Transformers with Small Datasets","created":"2021-06-07","cited_by_count":108},{"id":"2111.12933","title":"ML-Decoder: Scalable and Versatile Classification Head","created":"2021-11-25","cited_by_count":79},{"id":"2205.03257","title":"Synthetic Data -- what, why and how?","created":"2022-05-06","cited_by_count":67},{"id":"1404.1869","title":"DenseNet: Implementing Efficient ConvNet Descriptor Pyramids","created":"2014-04-07","cited_by_count":66},{"id":"2102.08414","title":"Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies","created":"2021-02-16","cited_by_count":41},{"id":"2210.07240","title":"How to Train Vision Transformer on Small-scale Datasets?","created":"2022-10-13","cited_by_count":35},{"id":"2103.06132","title":"MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks","created":"2021-03-10","cited_by_count":32},{"id":"1902.00267","title":"ColorNet: Investigating the importance of color spaces for image classification","created":"2019-02-01","cited_by_count":31},{"id":"2112.13692","title":"Augmenting Convolutional networks with attention-based aggregation","created":"2021-12-27","cited_by_count":29},{"id":"2207.02842","title":"When does Bias Transfer in Transfer Learning?","created":"2022-07-06","cited_by_count":23},{"id":"2205.14375","title":"WaveMix: A Resource-efficient Neural Network for Image Analysis","created":"2022-05-28","cited_by_count":19},{"id":"2205.12755","title":"An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems","created":"2022-05-25","cited_by_count":16},{"id":"2205.10660","title":"Vision Transformers in 2022: An Update on Tiny ImageNet","created":"2022-05-21","cited_by_count":13},{"id":"2011.14660","title":"Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training","created":"2020-11-30","cited_by_count":12},{"id":"2004.09691","title":"A Data and Compute Efficient Design for Limited-Resources Deep Learning","created":"2020-04-21","cited_by_count":10},{"id":"2210.00471","title":"OCD: Learning to Overfit with Conditional Diffusion Models","created":"2022-10-02","cited_by_count":9},{"id":"1912.08136","title":"Direction Concentration Learning: Enhancing Congruency in Machine Learning","created":"2019-12-17","cited_by_count":5},{"id":"2211.00677","title":"Semi-Supervised Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection","created":"2022-11-01","cited_by_count":4},{"id":"2110.00199","title":"Perturbated Gradients Updating within Unit Space for Deep Learning","created":"2021-10-01","cited_by_count":3}],"next_cursor":null}