{"total":109,"rows":[{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"area":null},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855,"area":null},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519,"area":null},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435,"area":null},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360,"area":null},{"id":"2112.10762","title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","created":"2021-12-20","cited_by_count":152,"area":null},{"id":"2206.03126","title":"Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse","created":"2022-06-07","cited_by_count":141,"area":null},{"id":"2104.03516","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","created":"2021-04-08","cited_by_count":107,"area":null},{"id":"2101.08692","title":"Characterizing signal propagation to close the performance gap in unnormalized ResNets","created":"2021-01-21","cited_by_count":88,"area":null},{"id":"2103.05633","title":"Proof-of-Learning: Definitions and Practice","created":"2021-03-09","cited_by_count":84,"area":null},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2212.06152","title":"Accelerating Dataset Distillation via Model Augmentation","created":"2022-12-12","cited_by_count":62,"area":null},{"id":"2112.12782","title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","created":"2021-12-23","cited_by_count":55,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2206.06072","title":"Rank Diminishing in Deep Neural Networks","created":"2022-06-13","cited_by_count":47,"area":null},{"id":"2103.17268","title":"Fast Certified Robust Training with Short Warmup","created":"2021-03-31","cited_by_count":46,"area":null},{"id":"2302.10322","title":"Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation","created":"2023-02-20","cited_by_count":45,"area":null},{"id":"2205.02973","title":"Large Scale Transfer Learning for Differentially Private Image Classification","created":"2022-05-06","cited_by_count":41,"area":null},{"id":"2206.02768","title":"The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization","created":"2022-06-06","cited_by_count":41,"area":null},{"id":"2209.14764","title":"Model Zoos: A Dataset of Diverse Populations of Neural Network Models","created":"2022-09-29","cited_by_count":39,"area":null},{"id":"2306.06179","title":"Hidden symmetries of ReLU networks","created":"2023-06-09","cited_by_count":39,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2104.08135","title":"Sharp bounds for the number of regions of maxout networks and vertices of Minkowski sums","created":"2021-04-16","cited_by_count":37,"area":null},{"id":"2311.01906","title":"Simplifying Transformer Blocks","created":"2023-11-03","cited_by_count":37,"area":null},{"id":"2210.07240","title":"How to Train Vision Transformer on Small-scale Datasets?","created":"2022-10-13","cited_by_count":35,"area":null},{"id":"2106.04013","title":"The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization","created":"2021-06-07","cited_by_count":33,"area":null},{"id":"2111.13293","title":"KNAS: Green Neural Architecture Search","created":"2021-11-26","cited_by_count":33,"area":null},{"id":"2106.06615","title":"Precise characterization of the prior predictive distribution of deep ReLU networks","created":"2021-06-11","cited_by_count":28,"area":null},{"id":"2106.05956","title":"Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning","created":"2021-06-10","cited_by_count":25,"area":null},{"id":"2310.13545","title":"ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection","created":"2023-10-20","cited_by_count":25,"area":"diffusion"},{"id":"2212.14457","title":"Bayesian Interpolation with Deep Linear Networks","created":"2022-12-29","cited_by_count":21,"area":null},{"id":"2412.07224","title":"Parseval Regularization for Continual Reinforcement Learning","created":"2024-12-10","cited_by_count":21,"area":"deeprl"},{"id":"2307.06092","title":"Quantitative CLTs in Deep Neural Networks","created":"2023-07-12","cited_by_count":20,"area":null},{"id":"2302.12250","title":"Phase diagram of early training dynamics in deep neural networks: effect of the learning rate, depth, and width","created":"2023-02-23","cited_by_count":19,"area":null},{"id":"2402.07193","title":"Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent","created":"2024-02-11","cited_by_count":19,"area":null},{"id":"2206.06929","title":"Scaling ResNets in the Large-depth Regime","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2102.10492","title":"Deep ReLU Networks Preserve Expected Length","created":"2021-02-21","cited_by_count":17,"area":null},{"id":"2104.08215","title":"\"BNN - BN = ?\": Training Binary Neural Networks without Batch Normalization","created":"2021-04-16","cited_by_count":17,"area":null},{"id":"2505.24333","title":"Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation","created":"2025-05-30","cited_by_count":17,"area":null},{"id":"2309.08859","title":"Rethinking Learning Rate Tuning in the Era of Large Language Models","created":"2023-09-16","cited_by_count":16,"area":"lr"},{"id":"2106.15230","title":"Convolutional Hypercomplex Embeddings for Link Prediction","created":"2021-06-29","cited_by_count":15,"area":null},{"id":"2102.09924","title":"A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions","created":"2021-02-19","cited_by_count":14,"area":null},{"id":"2105.07741","title":"Activation function design for deep networks: linearity and effective initialisation","created":"2021-05-17","cited_by_count":13,"area":null},{"id":"2106.03743","title":"Proxy-Normalizing Activations to Match Batch Normalization while Removing Batch Dependence","created":"2021-06-07","cited_by_count":12,"area":null},{"id":"2205.08099","title":"Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey","created":"2022-05-17","cited_by_count":12,"area":null},{"id":"2212.07295","title":"Maximal Initial Learning Rates in Deep ReLU Networks","created":"2022-12-14","cited_by_count":11,"area":null},{"id":"2306.00945","title":"CS4ML: A general framework for active learning with arbitrary data based on Christoffel functions","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2306.05879","title":"FedWon: Triumphing Multi-domain Federated Learning Without Normalization","created":"2023-06-09","cited_by_count":11,"area":null},{"id":"2311.18718","title":"The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks","created":"2023-11-30","cited_by_count":11,"area":null},{"id":"2208.00238","title":"Improving Fine-tuning of Self-supervised Models with Contrastive Initialization","created":"2022-07-30","cited_by_count":10,"area":null},{"id":"2104.00277","title":"A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions","created":"2021-04-01","cited_by_count":9,"area":null},{"id":"2110.15288","title":"Hyper-Representations: Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction","created":"2021-10-28","cited_by_count":9,"area":null},{"id":"2112.14602","title":"Modified DDPG car-following model with a real-world human driving experience with CARLA simulator","created":"2021-12-29","cited_by_count":9,"area":"driving"},{"id":"2412.18283","title":"On the Local Complexity of Linear Regions in Deep ReLU Networks","created":"2024-12-24","cited_by_count":9,"area":null},{"id":"2107.13490","title":"Adaptive Precision Training (AdaPT): A dynamic fixed point quantized training approach for DNNs","created":"2021-07-28","cited_by_count":8,"area":null},{"id":"2204.03475","title":"Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results","created":"2022-04-07","cited_by_count":8,"area":null},{"id":"2103.17174","title":"Using activation histograms to bound the number of affine regions in ReLU feed-forward neural networks","created":"2021-03-31","cited_by_count":7,"area":null},{"id":"2208.12190","title":"CAS4DL: Christoffel Adaptive Sampling for function approximation via Deep Learning","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2301.12056","title":"Variational Latent Branching Model for Off-Policy Evaluation","created":"2023-01-28","cited_by_count":6,"area":null},{"id":"2308.12585","title":"Persistent learning signals and working memory without continuous attractors","created":"2023-08-24","cited_by_count":6,"area":null},{"id":"2309.10639","title":"Geometric structure of Deep Learning networks and construction of global ${\\mathcal L}^2$ minimizers","created":"2023-09-19","cited_by_count":6,"area":null},{"id":"2506.16884","title":"The Importance of Being Lazy: Scaling Limits of Continual Learning","created":"2025-06-20","cited_by_count":6,"area":null},{"id":"2109.08958","title":"AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks","created":"2021-09-18","cited_by_count":5,"area":null},{"id":"2306.00809","title":"Initial Guessing Bias: How Untrained Networks Favor Some Classes","created":"2023-06-01","cited_by_count":5,"area":null},{"id":"2310.07765","title":"Feature Learning and Generalization in Deep Networks with Orthogonal Weights","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2312.17306","title":"Gradient Flossing: Improving Gradient Descent through Dynamic Control of Jacobians","created":"2023-12-28","cited_by_count":5,"area":null},{"id":"2105.13890","title":"Towards Efficient Full 8-bit Integer DNN Online Training on Resource-limited Devices without Batch Normalization","created":"2021-05-27","cited_by_count":4,"area":null},{"id":"2205.00428","title":"Analysis of Diffractive Neural Networks for Seeing Through Random Diffusers","created":"2022-05-01","cited_by_count":4,"area":null},{"id":"2309.10370","title":"Geometric structure of shallow neural networks and constructive ${\\mathcal L}^2$ cost minimization","created":"2023-09-19","cited_by_count":4,"area":null},{"id":"2401.10178","title":"Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields","created":"2024-01-18","cited_by_count":4,"area":null},{"id":"2410.05052","title":"Initialization of Large Language Models via Reparameterization to Mitigate Loss Spikes","created":"2024-10-07","cited_by_count":4,"area":null},{"id":"2202.00282","title":"Stabilizing Spiking Neuron Training","created":"2022-02-01","cited_by_count":3,"area":null},{"id":"2306.11668","title":"Principles for Initialization and Architecture Selection in Graph Neural Networks with ReLU Activations","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2311.06138","title":"Minimum norm interpolation by perceptra: Explicit regularization and implicit bias","created":"2023-11-10","cited_by_count":3,"area":null},{"id":"2404.02235","title":"Is Exploration All You Need? Effective Exploration Characteristics for Transfer in Reinforcement Learning","created":"2024-04-02","cited_by_count":3,"area":"deeprl"},{"id":"2508.01519","title":"The Vanishing Gradient Problem for Stiff Neural Differential Equations","created":"2025-08-02","cited_by_count":3,"area":null},{"id":"2107.11678","title":"Deep-learning-driven Reliable Single-pixel Imaging with Uncertainty Approximation","created":"2021-07-24","cited_by_count":2,"area":null},{"id":"2110.13107","title":"The Nuts and Bolts of Adopting Transformer in GANs","created":"2021-10-25","cited_by_count":2,"area":null},{"id":"2212.12086","title":"Eigenvalue initialisation and regularisation for Koopman autoencoders","created":"2022-12-23","cited_by_count":2,"area":null},{"id":"2311.15487","title":"Global $\\mathcal{L}^2$ minimization at uniform exponential rate via geometrically adapted gradient descent in Deep Learning","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2112.12299","title":"A Robust Initialization of Residual Blocks for Effective ResNet Training without Batch Normalization","created":"2021-12-23","cited_by_count":1,"area":null},{"id":"2301.06956","title":"Expected Gradients of Maxout Networks and Consequences to Parameter Initialization","created":"2023-01-17","cited_by_count":1,"area":null},{"id":"2402.00195","title":"Dataset Condensation Driven Machine Unlearning","created":"2024-01-31","cited_by_count":1,"area":"safety"},{"id":"2407.02653","title":"Joint Segmentation and Image Reconstruction with Error Prediction in Photoacoustic Imaging using Deep Learning","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2412.09853","title":"Understand the Effectiveness of Shortcuts through the Lens of DCA","created":"2024-12-13","cited_by_count":1,"area":null},{"id":"2506.10463","title":"Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2607.05031","title":"LLM-Based Test Oracles: Source-of-Authority Taxonomy -- A Systematic Literature Review","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2104.03757","title":"Predicting Inflation with Recurrent Neural Networks","created":"2021-04-08","cited_by_count":0,"area":null},{"id":"2108.10066","title":"Dynamic Neural Network Architectural and Topological Adaptation and Related Methods -- A Survey","created":"2021-07-28","cited_by_count":0,"area":null},{"id":"2110.07758","title":"\"Knights\": First Place Submission for VIPriors21 Action Recognition Challenge at ICCV 2021","created":"2021-10-14","cited_by_count":0,"area":null},{"id":"2111.02155","title":"A Johnson--Lindenstrauss Framework for Randomly Initialized CNNs","created":"2021-11-03","cited_by_count":0,"area":null},{"id":"2201.02397","title":"Neural calibration of hidden inhomogeneous Markov chains -- Information decompression in life insurance","created":"2022-01-07","cited_by_count":0,"area":null},{"id":"2204.04235","title":"Vision-Based American Sign Language Classification Approach via Deep Learning","created":"2022-04-08","cited_by_count":0,"area":null},{"id":"2205.08098","title":"Can We Do Better Than Random Start? The Power of Data Outsourcing","created":"2022-05-17","cited_by_count":0,"area":null},{"id":"2210.02411","title":"Dynamical Isometry for Residual Networks","created":"2022-10-05","cited_by_count":0,"area":null},{"id":"2211.11077","title":"Unifying Tracking and Image-Video Object Detection","created":"2022-11-20","cited_by_count":0,"area":null},{"id":"2306.09320","title":"Learnable Weight Initialization for Volumetric Medical Image Segmentation","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2311.07065","title":"On non-approximability of zero loss global ${\\mathcal L}^2$ minimizers by gradient descent in Deep Learning","created":"2023-11-13","cited_by_count":0,"area":null},{"id":"2403.14019","title":"Searching Search Spaces: Meta-evolving a Geometric Encoding for Neural Networks","created":"2024-03-20","cited_by_count":0,"area":null},{"id":"2502.01247","title":"Polynomial, trigonometric, and tropical activations","created":"2025-02-03","cited_by_count":0,"area":null}],"next_cursor":"100"}