{"total":153,"rows":[{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361,"area":null},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293,"area":null},{"id":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169,"area":null},{"id":"2110.03141","title":"Efficient Sharpness-aware Minimization for Improved Training of Neural Networks","created":"2021-10-07","cited_by_count":137,"area":null},{"id":"2202.03599","title":"Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning","created":"2022-02-08","cited_by_count":122,"area":null},{"id":"2101.05022","title":"Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels","created":"2021-01-13","cited_by_count":118,"area":null},{"id":"2105.12723","title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding","created":"2021-05-26","cited_by_count":97,"area":null},{"id":"2205.14083","title":"Sharpness-Aware Training for Free","created":"2022-05-27","cited_by_count":95,"area":null},{"id":"2108.04392","title":"Rethinking Architecture Selection in Differentiable NAS","created":"2021-08-10","cited_by_count":92,"area":null},{"id":"2206.04920","title":"Fisher SAM: Information Geometry and Sharpness Aware Minimisation","created":"2022-06-10","cited_by_count":84,"area":null},{"id":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78,"area":null},{"id":"2303.03108","title":"Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization","created":"2023-03-03","cited_by_count":57,"area":null},{"id":"2108.04204","title":"Meta Gradient Adversarial Attack","created":"2021-08-09","cited_by_count":55,"area":null},{"id":"2201.03299","title":"Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks","created":"2022-01-10","cited_by_count":55,"area":null},{"id":"2403.12350","title":"Friendly Sharpness-Aware Minimization","created":"2024-03-19","cited_by_count":53,"area":null},{"id":"2304.14647","title":"An Adaptive Policy to Employ Sharpness-Aware Minimization","created":"2023-04-28","cited_by_count":43,"area":null},{"id":"2210.06441","title":"How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization","created":"2022-10-12","cited_by_count":40,"area":null},{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39,"area":null},{"id":"2202.12513","title":"TeachAugment: Data Augmentation Optimization Using Teacher Knowledge","created":"2022-02-25","cited_by_count":37,"area":null},{"id":"2106.02733","title":"DISCO: accurate Discrete Scale Convolutions","created":"2021-06-04","cited_by_count":36,"area":null},{"id":"2205.10217","title":"Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization","created":"2022-05-20","cited_by_count":36,"area":null},{"id":"2101.01761","title":"AutoDropout: Learning Dropout Patterns to Regularize Deep Networks","created":"2021-01-05","cited_by_count":35,"area":null},{"id":"2103.05471","title":"Contrastive Neural Architecture Search with Neural Architecture Comparators","created":"2021-03-08","cited_by_count":34,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2302.05086","title":"Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples","created":"2023-02-10","cited_by_count":32,"area":null},{"id":"2301.00364","title":"Generalizable Black-Box Adversarial Attack with Meta Learning","created":"2023-01-01","cited_by_count":29,"area":null},{"id":"2304.13410","title":"Improving Adversarial Transferability via Intermediate-level Perturbation Decay","created":"2023-04-26","cited_by_count":29,"area":null},{"id":"2112.11435","title":"Learned Queries for Efficient Local Attention","created":"2021-12-21","cited_by_count":27,"area":null},{"id":"2206.14502","title":"RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness","created":"2022-06-29","cited_by_count":27,"area":null},{"id":"2106.07085","title":"Survey: Image Mixing and Deleting for Data Augmentation","created":"2021-06-13","cited_by_count":26,"area":null},{"id":"2203.15207","title":"Generalizing Few-Shot NAS with Gradient Matching","created":"2022-03-29","cited_by_count":25,"area":null},{"id":"2209.08473","title":"Bootstrap Generalization Ability from Loss Landscape Perspective","created":"2022-09-18","cited_by_count":16,"area":null},{"id":"2302.00704","title":"Pathologies of Predictive Diversity in Deep Ensembles","created":"2023-02-01","cited_by_count":16,"area":null},{"id":"2103.14545","title":"DivAug: Plug-in Automated Data Augmentation with Explicit Diversity Maximization","created":"2021-03-26","cited_by_count":15,"area":null},{"id":"2112.08796","title":"Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing","created":"2021-12-16","cited_by_count":15,"area":null},{"id":"2203.06844","title":"RecursiveMix: Mixed Learning with History","created":"2022-03-14","cited_by_count":15,"area":null},{"id":"2107.09887","title":"An overview of mixing augmentation methods and augmentation strategies","created":"2021-07-21","cited_by_count":14,"area":null},{"id":"2203.09962","title":"Randomized Sharpness-Aware Training for Boosting Computational Efficiency in Deep Learning","created":"2022-03-18","cited_by_count":14,"area":null},{"id":"2104.09874","title":"Boosting Masked Face Recognition with Multi-Task ArcFace","created":"2021-04-20","cited_by_count":13,"area":null},{"id":"2109.01359","title":"CAM-loss: Towards Learning Spatially Discriminative Feature Representations","created":"2021-09-03","cited_by_count":13,"area":null},{"id":"2110.11111","title":"A Deep Insight into Measuring Face Image Utility with General and Face-specific Image Quality Metrics","created":"2021-10-21","cited_by_count":13,"area":null},{"id":"2309.04747","title":"When to Learn What: Model-Adaptive Data Augmentation Curriculum","created":"2023-09-09","cited_by_count":13,"area":null},{"id":"2210.13664","title":"Mitigating Gender Bias in Face Recognition Using the von Mises-Fisher Mixture Model","created":"2022-10-24","cited_by_count":12,"area":null},{"id":"2403.19588","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","created":"2024-03-28","cited_by_count":12,"area":null},{"id":"2111.07492","title":"Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks","created":"2021-11-15","cited_by_count":11,"area":null},{"id":"2210.12864","title":"K-SAM: Sharpness-Aware Minimization at the Speed of SGD","created":"2022-10-23","cited_by_count":10,"area":null},{"id":"2302.09738","title":"Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning","created":"2023-02-20","cited_by_count":10,"area":null},{"id":"2312.13555","title":"CR-SAM: Curvature Regularized Sharpness-Aware Minimization","created":"2023-12-21","cited_by_count":10,"area":null},{"id":"2405.01725","title":"Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey","created":"2024-05-02","cited_by_count":10,"area":null},{"id":"2101.01165","title":"Where Do Deep Fakes Look? Synthetic Face Detection via Gaze Tracking","created":"2021-01-04","cited_by_count":9,"area":null},{"id":"2105.08095","title":"Automatic Fault Detection for Deep Learning Programs Using Graph Transformations","created":"2021-05-17","cited_by_count":9,"area":null},{"id":"2209.08907","title":"Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning","created":"2022-09-19","cited_by_count":9,"area":null},{"id":"2103.11099","title":"Local Patch AutoAugment with Multi-Agent Collaboration","created":"2021-03-20","cited_by_count":8,"area":null},{"id":"2401.07250","title":"Stabilizing Sharpness-aware Minimization Through A Simple Renormalization Strategy","created":"2024-01-14","cited_by_count":8,"area":null},{"id":"2103.08640","title":"UPANets: Learning from the Universal Pixel Attention Networks","created":"2021-03-15","cited_by_count":7,"area":null},{"id":"2105.00717","title":"Synthetic Data for Model Selection","created":"2021-05-03","cited_by_count":7,"area":null},{"id":"2108.11939","title":"Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2111.13841","title":"Adaptive Perturbation for Adversarial Attack","created":"2021-11-27","cited_by_count":7,"area":null},{"id":"2112.04827","title":"Explainability of the Implications of Supervised and Unsupervised Face Image Quality Estimations Through Activation Map Variation Analyses in Face Recognition Models","created":"2021-12-09","cited_by_count":7,"area":null},{"id":"2309.09982","title":"Introspective Deep Metric Learning","created":"2023-09-11","cited_by_count":7,"area":null},{"id":"2301.09245","title":"Towards NeuroAI: Introducing Neuronal Diversity into Artificial Neural Networks","created":"2023-01-23","cited_by_count":6,"area":null},{"id":"2305.11739","title":"Survey of Automatic Plankton Image Recognition: Challenges, Existing Solutions and Future Perspectives","created":"2023-05-19","cited_by_count":6,"area":null},{"id":"2307.00592","title":"X-MLP: A Patch Embedding-Free MLP Architecture for Vision","created":"2023-07-02","cited_by_count":6,"area":null},{"id":"2307.00631","title":"Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers","created":"2023-07-02","cited_by_count":6,"area":null},{"id":"2108.01110","title":"Batch Normalization Preconditioning for Neural Network Training","created":"2021-08-02","cited_by_count":5,"area":null},{"id":"2110.04248","title":"Observations on K-image Expansion of Image-Mixing Augmentation for Classification","created":"2021-10-08","cited_by_count":5,"area":null},{"id":"2312.13118","title":"LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogate","created":"2023-12-20","cited_by_count":5,"area":null},{"id":"2406.08001","title":"Asymptotic Unbiased Sample Sampling to Speed Up Sharpness-Aware Minimization","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2410.05500","title":"Residual Kolmogorov-Arnold Network for Enhanced Deep Learning","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2211.17180","title":"Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think","created":"2022-11-30","cited_by_count":4,"area":null},{"id":"2306.17466","title":"MedAugment: Universal Automatic Data Augmentation Plug-in for Medical Image Analysis","created":"2023-06-30","cited_by_count":4,"area":null},{"id":"2403.04206","title":"GRAWA: Gradient-based Weighted Averaging for Distributed Training of Deep Learning Models","created":"2024-03-07","cited_by_count":4,"area":null},{"id":"2508.17232","title":"Curvature Learning for Generalization of Hyperbolic Neural Networks","created":"2025-08-24","cited_by_count":4,"area":null},{"id":"2101.04789","title":"Improving Classification Accuracy with Graph Filtering","created":"2021-01-12","cited_by_count":3,"area":null},{"id":"2103.06583","title":"Preprint: Norm Loss: An efficient yet effective regularization method for deep neural networks","created":"2021-03-11","cited_by_count":3,"area":null},{"id":"2105.11025","title":"Compressing Heavy-Tailed Weight Matrices for Non-Vacuous Generalization Bounds","created":"2021-05-23","cited_by_count":3,"area":null},{"id":"2105.15010","title":"Query Attack by Multi-Identity Surrogates","created":"2021-05-31","cited_by_count":3,"area":null},{"id":"2108.08205","title":"An Attention Module for Convolutional Neural Networks","created":"2021-08-18","cited_by_count":3,"area":null},{"id":"2109.02345","title":"Tensor Normalization and Full Distribution Training","created":"2021-09-06","cited_by_count":3,"area":null},{"id":"2111.00487","title":"Smart(Sampling)Augment: Optimal and Efficient Data Augmentation for Semantic Segmentation","created":"2021-10-31","cited_by_count":3,"area":null},{"id":"2111.11940","title":"PAM: Pose Attention Module for Pose-Invariant Face Recognition","created":"2021-11-23","cited_by_count":3,"area":null},{"id":"2211.07245","title":"Assessing Uncertainty in Similarity Scoring: Performance & Fairness in Face Recognition","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2307.04443","title":"Search-time Efficient Device Constraints-Aware Neural Architecture Search","created":"2023-07-10","cited_by_count":3,"area":null},{"id":"2307.11334","title":"Improving Transferability of Adversarial Examples via Bayesian Attacks","created":"2023-07-21","cited_by_count":3,"area":null},{"id":"2311.10807","title":"SENetV2: Aggregated dense layer for channelwise and global representations","created":"2023-11-17","cited_by_count":3,"area":null},{"id":"2401.13193","title":"Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN","created":"2024-01-24","cited_by_count":3,"area":null},{"id":"2504.07635","title":"Generative Artificial Intelligence for Internet of Things Computing: A Systematic Survey","created":"2025-04-10","cited_by_count":3,"area":null},{"id":"2604.24990","title":"A New Kind of Network? Review and Reference Implementation of Neural Cellular Automata","created":"2026-04-27","cited_by_count":3,"area":null},{"id":"2103.17272","title":"Efficient Large-Scale Face Clustering Using an Online Mixture of Gaussians","created":"2021-03-31","cited_by_count":2,"area":null},{"id":"2111.01742","title":"LogAvgExp Provides a Principled and Performant Global Pooling Operator","created":"2021-11-02","cited_by_count":2,"area":null},{"id":"2201.02149","title":"Bio-inspired Min-Nets Improve the Performance and Robustness of Deep Networks","created":"2022-01-06","cited_by_count":2,"area":null},{"id":"2205.09615","title":"EXACT: How to Train Your Accuracy","created":"2022-05-19","cited_by_count":2,"area":null},{"id":"2310.04179","title":"Entropic Score metric: Decoupling Topology and Size in Training-free NAS","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2409.13173","title":"Bilateral Sharpness-Aware Minimization for Flatter Minima","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2412.12473","title":"A Method for Enhancing Generalization of Adam by Multiple Integrations","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2505.23866","title":"Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2101.04028","title":"Unchain the Search Space with Hierarchical Differentiable Architecture Search","created":"2021-01-11","cited_by_count":1,"area":null},{"id":"2106.04921","title":"Self-supervised Feature Enhancement: Applying Internal Pretext Task to Supervised Learning","created":"2021-06-09","cited_by_count":1,"area":null},{"id":"2106.04922","title":"Self-supervision of Feature Transformation for Further Improving Supervised Learning","created":"2021-06-09","cited_by_count":1,"area":null},{"id":"2107.08421","title":"Feature Mining: A Novel Training Strategy for Convolutional Neural Network","created":"2021-07-18","cited_by_count":1,"area":null}],"next_cursor":"100"}