{"list":"other","total":83,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"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":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"1312.6184","title":"Do Deep Nets Really Need to be Deep?","created":"2013-12-21","cited_by_count":474},{"id":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"1611.02167","title":"Designing Neural Network Architectures using Reinforcement Learning","created":"2016-11-07","cited_by_count":279},{"id":"1910.04465","title":"Searching for A Robust Neural Architecture in Four GPU Hours","created":"2019-10-10","cited_by_count":260},{"id":"2006.02903","title":"A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions","created":"2020-06-01","cited_by_count":254},{"id":"2303.16196","title":"SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis","created":"2023-03-28","cited_by_count":247},{"id":"1708.05344","title":"SMASH: One-Shot Model Architecture Search through HyperNetworks","created":"2017-08-17","cited_by_count":202},{"id":"1802.07191","title":"Neural Architecture Search with Bayesian Optimisation and Optimal Transport","created":"2018-02-11","cited_by_count":195},{"id":"2003.11142","title":"BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models","created":"2020-03-24","cited_by_count":188},{"id":"2107.00651","title":"AutoFormer: Searching Transformers for Visual Recognition","created":"2021-07-01","cited_by_count":188},{"id":"1910.11858","title":"BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search","created":"2019-10-25","cited_by_count":179},{"id":"1909.09656","title":"Understanding and Robustifying Differentiable Architecture Search","created":"2019-09-20","cited_by_count":178},{"id":"2002.05715","title":"Self-Distillation Amplifies Regularization in Hilbert Space","created":"2020-02-13","cited_by_count":173},{"id":"1907.01845","title":"FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search","created":"2019-07-03","cited_by_count":130},{"id":"1902.08142","title":"Evaluating the Search Phase of Neural Architecture Search","created":"2019-02-21","cited_by_count":120},{"id":"1907.09595","title":"MixConv: Mixed Depthwise Convolutional Kernels","created":"2019-07-22","cited_by_count":108},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83},{"id":"1911.13053","title":"Blockwisely Supervised Neural Architecture Search with Knowledge Distillation","created":"2019-11-29","cited_by_count":81},{"id":"2302.01330","title":"SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections","created":"2023-02-02","cited_by_count":72},{"id":"1912.12522","title":"NAS evaluation is frustratingly hard","created":"2019-12-28","cited_by_count":70},{"id":"2011.09011","title":"AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling","created":"2020-11-18","cited_by_count":66},{"id":"2103.12424","title":"BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search","created":"2021-03-23","cited_by_count":63},{"id":"2006.06936","title":"Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?","created":"2020-06-12","cited_by_count":59},{"id":"2207.14811","title":"StyleLight: HDR Panorama Generation for Lighting Estimation and Editing","created":"2022-07-29","cited_by_count":59},{"id":"2107.02960","title":"GLiT: Neural Architecture Search for Global and Local Image Transformer","created":"2021-07-07","cited_by_count":53},{"id":"2310.16831","title":"PERF: Panoramic Neural Radiance Field from a Single Panorama","created":"2023-10-25","cited_by_count":45},{"id":"2104.08760","title":"Solving Inefficiency of Self-supervised Representation Learning","created":"2021-04-18","cited_by_count":41},{"id":"2111.14725","title":"Searching the Search Space of Vision Transformer","created":"2021-11-29","cited_by_count":41},{"id":"2003.12056","title":"Are Labels Necessary for Neural Architecture Search?","created":"2020-03-26","cited_by_count":37},{"id":"2102.07954","title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","created":"2021-02-16","cited_by_count":36},{"id":"2101.11834","title":"Neural Architecture Search with Random Labels","created":"2021-01-28","cited_by_count":33},{"id":"1704.08792","title":"DeepArchitect: Automatically Designing and Training Deep Architectures","created":"2017-04-28","cited_by_count":28},{"id":"1910.02543","title":"Improving One-shot NAS by Suppressing the Posterior Fading","created":"2019-10-06","cited_by_count":28},{"id":"1912.11234","title":"Computation Reallocation for Object Detection","created":"2019-12-24","cited_by_count":17},{"id":"2109.07222","title":"EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation","created":"2021-09-15","cited_by_count":15},{"id":"2111.10007","title":"FBNetV5: Neural Architecture Search for Multiple Tasks in One Run","created":"2021-11-19","cited_by_count":15},{"id":"2108.09671","title":"Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift","created":"2021-08-22","cited_by_count":14},{"id":"2110.08940","title":"Dynamic Slimmable Denoising Network","created":"2021-10-17","cited_by_count":9},{"id":"2211.14794","title":"Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs","created":"2022-11-27","cited_by_count":9},{"id":"1908.01314","title":"MoGA: Searching Beyond MobileNetV3","created":"2019-08-04","cited_by_count":8},{"id":"2109.10060","title":"DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers","created":"2021-09-21","cited_by_count":6},{"id":"2103.16889","title":"Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition","created":"2021-03-31","cited_by_count":2}],"next_cursor":null}