{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1607.02533","title":"Adversarial examples in the physical world","created":"2016-07-08","cited_by_count":1769},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1511.04508","title":"Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks","created":"2015-11-14","cited_by_count":678},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"1712.09665","title":"Adversarial Patch","created":"2017-12-27","cited_by_count":517},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362},{"id":"1912.12180","title":"Axial Attention in Multidimensional Transformers","created":"2019-12-20","cited_by_count":358},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338},{"id":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"2108.08839","title":"PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers","created":"2021-08-19","cited_by_count":286},{"id":"1703.08603","title":"Adversarial Examples for Semantic Segmentation and Object Detection","created":"2017-03-24","cited_by_count":275},{"id":"2107.00645","title":"Global Filter Networks for Image Classification","created":"2021-07-01","cited_by_count":260},{"id":"1703.00410","title":"Detecting Adversarial Samples from Artifacts","created":"2017-03-01","cited_by_count":245},{"id":"1910.10073","title":"Depth-Adaptive Transformer","created":"2019-10-22","cited_by_count":236},{"id":"2111.15668","title":"AdaViT: Adaptive Vision Transformers for Efficient Image Recognition","created":"2021-11-30","cited_by_count":228},{"id":"2111.15667","title":"Adaptive Token Sampling For Efficient Vision Transformers","created":"2021-11-30","cited_by_count":183},{"id":"1702.07811","title":"Adaptive Neural Networks for Efficient Inference","created":"2017-02-25","cited_by_count":163},{"id":"1711.11503","title":"Convolutional Networks with Adaptive Inference Graphs","created":"2017-11-30","cited_by_count":148},{"id":"2003.07326","title":"Resolution Adaptive Networks for Efficient Inference","created":"2020-03-16","cited_by_count":146},{"id":"2209.04881","title":"On The Computational Complexity of Self-Attention","created":"2022-09-11","cited_by_count":139},{"id":"1810.05331","title":"Dynamic Channel Pruning: Feature Boosting and Suppression","created":"2018-10-12","cited_by_count":129},{"id":"2110.11945","title":"SOFT: Softmax-free Transformer with Linear Complexity","created":"2021-10-22","cited_by_count":128},{"id":"1612.02297","title":"Spatially Adaptive Computation Time for Residual Networks","created":"2016-12-07","cited_by_count":118},{"id":"1912.03203","title":"Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference","created":"2019-12-06","cited_by_count":91},{"id":"1805.12549","title":"Channel Gating Neural Networks","created":"2018-05-29","cited_by_count":80},{"id":"1612.07767","title":"Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics","created":"2016-12-22","cited_by_count":77},{"id":"2110.03860","title":"Token Pooling in Vision Transformers","created":"2021-10-08","cited_by_count":69},{"id":"2010.02432","title":"A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference","created":"2020-10-06","cited_by_count":61},{"id":"1801.02108","title":"SBNet: Sparse Blocks Network for Fast Inference","created":"2018-01-07","cited_by_count":54},{"id":"2003.08866","title":"Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation","created":"2020-03-19","cited_by_count":51},{"id":"2003.12243","title":"Dynamic Region-Aware Convolution","created":"2020-03-27","cited_by_count":50},{"id":"2203.15859","title":"NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models","created":"2022-03-29","cited_by_count":50},{"id":"2203.08392","title":"Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?","created":"2022-03-16","cited_by_count":49},{"id":"1907.06627","title":"Batch-Shaping for Learning Conditional Channel Gated Networks","created":"2019-07-15","cited_by_count":42},{"id":"2206.08898","title":"SimA: Simple Softmax-free Attention for Vision Transformers","created":"2022-06-17","cited_by_count":32},{"id":"2002.06275","title":"TwinBERT: Distilling Knowledge to Twin-Structured BERT Models for Efficient Retrieval","created":"2020-02-14","cited_by_count":24},{"id":"1703.10332","title":"Dynamic Computational Time for Visual Attention","created":"2017-03-30","cited_by_count":23},{"id":"2209.09004","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","created":"2022-09-19","cited_by_count":21},{"id":"1710.03368","title":"Energy-efficient Amortized Inference with Cascaded Deep Classifiers","created":"2017-10-10","cited_by_count":15},{"id":"1911.07033","title":"S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search","created":"2019-11-16","cited_by_count":14},{"id":"1805.01556","title":"Pixel-wise Attentional Gating for Parsimonious Pixel Labeling","created":"2018-05-03","cited_by_count":12},{"id":"2210.00641","title":"DARTFormer: Finding The Best Type Of Attention","created":"2022-10-02","cited_by_count":3}],"next_cursor":null}