{"list":"other","total":65,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"1807.03039","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","created":"2018-07-09","cited_by_count":1545},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1805.10965","title":"Lipschitz regularity of deep neural networks: analysis and efficient estimation","created":"2018-05-28","cited_by_count":415},{"id":"1811.00995","title":"Invertible Residual Networks","created":"2018-11-02","cited_by_count":365},{"id":"1704.08847","title":"Parseval Networks: Improving Robustness to Adversarial Examples","created":"2017-04-28","cited_by_count":293},{"id":"1906.04893","title":"Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks","created":"2019-06-12","cited_by_count":293},{"id":"1802.10062","title":"CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes","created":"2018-02-27","cited_by_count":267},{"id":"1811.05381","title":"Sorting out Lipschitz function approximation","created":"2018-11-13","cited_by_count":213},{"id":"2201.09792","title":"Patches Are All You Need?","created":"2022-01-24","cited_by_count":201},{"id":"1806.05393","title":"Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks","created":"2018-06-14","cited_by_count":176},{"id":"2405.15682","title":"The Road Less Scheduled","created":"2024-05-24","cited_by_count":163},{"id":"2105.12806","title":"A Universal Law of Robustness via Isoperimetry","created":"2021-05-26","cited_by_count":151},{"id":"1911.12207","title":"Orthogonal Convolutional Neural Networks","created":"2019-11-27","cited_by_count":123},{"id":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114},{"id":"2104.07167","title":"Orthogonalizing Convolutional Layers with the Cayley Transform","created":"2021-04-14","cited_by_count":105},{"id":"1805.10408","title":"The Singular Values of Convolutional Layers","created":"2018-05-26","cited_by_count":95},{"id":"1911.00937","title":"Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks","created":"2019-11-03","cited_by_count":87},{"id":"1803.05649","title":"Sylvester Normalizing Flows for Variational Inference","created":"2018-03-15","cited_by_count":72},{"id":"2105.11417","title":"Skew Orthogonal Convolutions","created":"2021-05-24","cited_by_count":67},{"id":"2110.12690","title":"A Dynamical System Perspective for Lipschitz Neural Networks","created":"2021-10-25","cited_by_count":60},{"id":"2303.03169","title":"A Unified Algebraic Perspective on Lipschitz Neural Networks","created":"2023-03-06","cited_by_count":60},{"id":"1903.01014","title":"Lipschitz Certificates for Layered Network Structures Driven by Averaged Activation Operators","created":"2019-03-03","cited_by_count":55},{"id":"2301.11526","title":"Direct Parameterization of Lipschitz-Bounded Deep Networks","created":"2023-01-27","cited_by_count":51},{"id":"1906.04659","title":"Stable Rank Normalization for Improved Generalization in Neural Networks and GANs","created":"2019-06-11","cited_by_count":41},{"id":"2006.16992","title":"Deep Isometric Learning for Visual Recognition","created":"2020-06-30","cited_by_count":39},{"id":"2208.03160","title":"Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks","created":"2022-08-05","cited_by_count":39},{"id":"2011.02281","title":"Convolutional Proximal Neural Networks and Plug-and-Play Algorithms","created":"2020-11-04","cited_by_count":36},{"id":"2210.11620","title":"LOT: Layer-wise Orthogonal Training on Improving $\\ell_2$ Certified Robustness","created":"2022-10-20","cited_by_count":33},{"id":"2104.05097","title":"Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks","created":"2021-04-11","cited_by_count":30},{"id":"2006.06520","title":"Achieving robustness in classification using optimal transport with hinge regularization","created":"2020-06-11","cited_by_count":27},{"id":"2203.05483","title":"projUNN: efficient method for training deep networks with unitary matrices","created":"2022-03-10","cited_by_count":27},{"id":"2306.11251","title":"Lipschitz Singularities in Diffusion Models","created":"2023-06-20","cited_by_count":21},{"id":"2305.16173","title":"Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration","created":"2023-05-25","cited_by_count":19},{"id":"2108.05623","title":"Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks","created":"2021-08-12","cited_by_count":16},{"id":"2311.16833","title":"1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness","created":"2023-11-28","cited_by_count":16},{"id":"2305.16202","title":"DP-SGD Without Clipping: The Lipschitz Neural Network Way","created":"2023-05-25","cited_by_count":11},{"id":"2406.10019","title":"Group and Shuffle: Efficient Structured Orthogonal Parametrization","created":"2024-06-14","cited_by_count":11},{"id":"2211.08453","title":"Improved techniques for deterministic l2 robustness","created":"2022-11-15","cited_by_count":9},{"id":"2211.13771","title":"Towards Practical Control of Singular Values of Convolutional Layers","created":"2022-11-24","cited_by_count":9},{"id":"2303.11835","title":"Lipschitz-bounded 1D convolutional neural networks using the Cayley transform and the controllability Gramian","created":"2023-03-20","cited_by_count":9},{"id":"2405.01125","title":"Lipschitz constant estimation for general neural network architectures using control tools","created":"2024-05-02","cited_by_count":8},{"id":"2106.09121","title":"Scaling-up Diverse Orthogonal Convolutional Networks with a Paraunitary Framework","created":"2021-06-16","cited_by_count":7},{"id":"2402.16017","title":"Spectrum Extraction and Clipping for Implicitly Linear Layers","created":"2024-02-25","cited_by_count":7},{"id":"2409.11859","title":"Tight and Efficient Upper Bound on Spectral Norm of Convolutional Layers","created":"2024-09-18","cited_by_count":7},{"id":"2206.06854","title":"On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective","created":"2022-06-14","cited_by_count":6},{"id":"2402.00240","title":"Spectral Norm of Convolutional Layers with Circular and Zero Paddings","created":"2024-01-31","cited_by_count":4},{"id":"2412.04245","title":"Intriguing Properties of Robust Classification","created":"2024-12-05","cited_by_count":3},{"id":"2411.17887","title":"A Parallel Scan Algorithm in the Tensor Core Unit Model","created":"2024-11-26","cited_by_count":2},{"id":"2401.03384","title":"conv_einsum: A Framework for Representation and Fast Evaluation of Multilinear Operations in Convolutional Tensorial Neural Networks","created":"2024-01-07","cited_by_count":1}],"next_cursor":null}