{"total":87,"rows":[{"id":"2101.06329","title":"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning","created":"2021-01-15","cited_by_count":301,"area":null},{"id":"2204.11312","title":"EMOCA: Emotion Driven Monocular Face Capture and Animation","created":"2022-04-24","cited_by_count":255,"area":null},{"id":"2103.10158","title":"TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation","created":"2021-03-18","cited_by_count":227,"area":null},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172,"area":null},{"id":"2204.08610","title":"Image Data Augmentation for Deep Learning: A Survey","created":"2022-04-19","cited_by_count":96,"area":null},{"id":"2111.05177","title":"On Training Implicit Models","created":"2021-11-09","cited_by_count":75,"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":"2106.15324","title":"Effective Evaluation of Deep Active Learning on Image Classification Tasks","created":"2021-06-16","cited_by_count":37,"area":null},{"id":"2110.02424","title":"Spectral Bias in Practice: The Role of Function Frequency in Generalization","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2202.12513","title":"TeachAugment: Data Augmentation Optimization Using Teacher Knowledge","created":"2022-02-25","cited_by_count":37,"area":null},{"id":"2104.04282","title":"Direct Differentiable Augmentation Search","created":"2021-04-09","cited_by_count":28,"area":null},{"id":"2102.04154","title":"Efficient Certified Defenses Against Patch Attacks on Image Classifiers","created":"2021-02-08","cited_by_count":24,"area":null},{"id":"2105.01015","title":"Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization","created":"2021-05-03","cited_by_count":19,"area":null},{"id":"2106.03357","title":"Evaluating State-of-the-Art Classification Models Against Bayes Optimality","created":"2021-06-07","cited_by_count":16,"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":"2508.12720","title":"Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting","created":"2025-08-18","cited_by_count":14,"area":null},{"id":"2103.15685","title":"Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation","created":"2021-03-29","cited_by_count":13,"area":null},{"id":"2210.00094","title":"Improving Robustness with Adaptive Weight Decay","created":"2022-09-30","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":"2409.06290","title":"EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classification","created":"2024-09-10","cited_by_count":13,"area":null},{"id":"2104.00597","title":"One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking","created":"2021-04-01","cited_by_count":12,"area":null},{"id":"2211.01407","title":"On the Informativeness of Supervision Signals","created":"2022-11-02","cited_by_count":12,"area":null},{"id":"2112.02862","title":"SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation","created":"2021-12-06","cited_by_count":10,"area":null},{"id":"2202.07184","title":"On the Origins of the Block Structure Phenomenon in Neural Network Representations","created":"2022-02-15","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":"2206.15015","title":"Exploring Temporally Dynamic Data Augmentation for Video Recognition","created":"2022-06-30","cited_by_count":9,"area":null},{"id":"2402.06656","title":"DiffsFormer: A Diffusion Transformer on Stock Factor Augmentation","created":"2024-02-05","cited_by_count":9,"area":"diffusion"},{"id":"2103.11099","title":"Local Patch AutoAugment with Multi-Agent Collaboration","created":"2021-03-20","cited_by_count":8,"area":null},{"id":"2106.02985","title":"Escaping Saddle Points Faster with Stochastic Momentum","created":"2021-06-05","cited_by_count":8,"area":null},{"id":"2305.09773","title":"Towards Modeling Human Attention from Eye Movements for Neural Source Code Summarization","created":"2023-05-16","cited_by_count":8,"area":null},{"id":"2105.00717","title":"Synthetic Data for Model Selection","created":"2021-05-03","cited_by_count":7,"area":null},{"id":"2105.03014","title":"BasisNet: Two-stage Model Synthesis for Efficient Inference","created":"2021-05-07","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":"2211.16040","title":"AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification","created":"2022-11-29","cited_by_count":7,"area":null},{"id":"2405.11467","title":"AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation","created":"2024-05-19","cited_by_count":7,"area":null},{"id":"2101.08237","title":"An Empirical Study and Analysis on Open-Set Semi-Supervised Learning","created":"2021-01-19","cited_by_count":6,"area":null},{"id":"2306.00169","title":"Inconsistency, Instability, and Generalization Gap of Deep Neural Network Training","created":"2023-05-31","cited_by_count":6,"area":null},{"id":"2105.03155","title":"Diffusion Mechanism in Residual Neural Network: Theory and Applications","created":"2021-05-07","cited_by_count":5,"area":null},{"id":"2110.10536","title":"Improving Model Generalization by Agreement of Learned Representations from Data Augmentation","created":"2021-10-20","cited_by_count":5,"area":null},{"id":"2207.06658","title":"Universal Adaptive Data Augmentation","created":"2022-07-14","cited_by_count":5,"area":null},{"id":"2508.08004","title":"Sample-aware RandAugment: Search-free Automatic Data Augmentation for Effective Image Recognition","created":"2025-08-11","cited_by_count":5,"area":null},{"id":"2107.03719","title":"Bag of Tricks for Neural Architecture Search","created":"2021-07-08","cited_by_count":4,"area":null},{"id":"2110.09168","title":"Domain Generalisation for Apparent Emotional Facial Expression Recognition across Age-Groups","created":"2021-10-18","cited_by_count":4,"area":null},{"id":"2204.02027","title":"A Survey on Dropout Methods and Experimental Verification in Recommendation","created":"2022-04-05","cited_by_count":4,"area":null},{"id":"2204.06562","title":"Estimating Structural Disparities for Face Models","created":"2022-04-13","cited_by_count":4,"area":null},{"id":"2307.11988","title":"Sparse then Prune: Toward Efficient Vision Transformers","created":"2023-07-22","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":"2103.15425","title":"FocusedDropout for Convolutional Neural Network","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2104.08364","title":"Sync-Switch: Hybrid Parameter Synchronization for Distributed Deep Learning","created":"2021-04-16","cited_by_count":3,"area":null},{"id":"2106.11528","title":"Recent Deep Semi-supervised Learning Approaches and Related Works","created":"2021-06-22","cited_by_count":3,"area":null},{"id":"2110.07981","title":"Reappraising Domain Generalization in Neural Networks","created":"2021-10-15","cited_by_count":3,"area":null},{"id":"2405.06354","title":"KeepOriginalAugment: Single Image-based Better Information-Preserving Data Augmentation Approach","created":"2024-05-10","cited_by_count":3,"area":null},{"id":"2502.18153","title":"SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2102.00511","title":"Fine-tuning Handwriting Recognition systems with Temporal Dropout","created":"2021-01-31","cited_by_count":2,"area":null},{"id":"2102.12985","title":"A Novel Framework for Neural Architecture Search in the Hill Climbing Domain","created":"2021-02-22","cited_by_count":2,"area":null},{"id":"2211.13332","title":"Learning Compact Features via In-Training Representation Alignment","created":"2022-11-23","cited_by_count":2,"area":null},{"id":"2307.02337","title":"FAM: Relative Flatness Aware Minimization","created":"2023-07-05","cited_by_count":2,"area":null},{"id":"2401.03753","title":"Color-$S^{4}L$: Self-supervised Semi-supervised Learning with Image Colorization","created":"2024-01-08","cited_by_count":2,"area":null},{"id":"2403.15726","title":"Convection-Diffusion Equation: A Theoretically Certified Framework for Neural Networks","created":"2024-03-23","cited_by_count":2,"area":null},{"id":"2101.02397","title":"A Comprehensive Study on Optimization Strategies for Gradient Descent In Deep Learning","created":"2021-01-07","cited_by_count":1,"area":null},{"id":"2106.08693","title":"ParticleAugment: Sampling-Based Data Augmentation","created":"2021-06-16","cited_by_count":1,"area":null},{"id":"2209.01848","title":"A Principled Evaluation Protocol for Comparative Investigation of the Effectiveness of DNN Classification Models on Similar-but-non-identical Datasets","created":"2022-09-05","cited_by_count":1,"area":null},{"id":"2305.02668","title":"LatentAugment: Dynamically Optimized Latent Probabilities of Data Augmentation","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2403.06382","title":"Pre-Trained Model Recommendation for Downstream Fine-tuning","created":"2024-03-11","cited_by_count":1,"area":null},{"id":"2403.08352","title":"Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2410.06478","title":"MaskBlur: Spatial and Angular Data Augmentation for Light Field Image Super-Resolution","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2509.16678","title":"IPF-RDA: An Information-Preserving Framework for Robust Data Augmentation","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2103.11820","title":"GPNAS: A Neural Network Architecture Search Framework Based on Graphical Predictor","created":"2021-03-19","cited_by_count":0,"area":null},{"id":"2103.15383","title":"Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions","created":"2021-03-29","cited_by_count":0,"area":null},{"id":"2301.00007","title":"Selected aspects of complex, hypercomplex and fuzzy neural networks","created":"2022-12-29","cited_by_count":0,"area":null},{"id":"2303.02081","title":"Unproportional mosaicing","created":"2023-03-03","cited_by_count":0,"area":null},{"id":"2304.10310","title":"LA3: Efficient Label-Aware AutoAugment","created":"2023-04-20","cited_by_count":0,"area":null},{"id":"2306.08460","title":"Improving Generalization in Meta-Learning via Meta-Gradient Augmentation","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2307.16664","title":"Generative models for wearables data","created":"2023-07-31","cited_by_count":0,"area":null},{"id":"2308.03236","title":"G-Mix: A Generalized Mixup Learning Framework Towards Flat Minima","created":"2023-08-07","cited_by_count":0,"area":null},{"id":"2311.15225","title":"One-bit Supervision for Image Classification: Problem, Solution, and Beyond","created":"2023-11-26","cited_by_count":0,"area":null},{"id":"2401.06244","title":"YOLO-Former: YOLO Shakes Hand With ViT","created":"2024-01-11","cited_by_count":0,"area":null},{"id":"2408.13426","title":"Optimal Layer Selection for Latent Data Augmentation","created":"2024-08-24","cited_by_count":0,"area":null},{"id":"2409.07940","title":"Control+Shift: Generating Controllable Distribution Shifts","created":"2024-09-12","cited_by_count":0,"area":null},{"id":"2411.10891","title":"ChannelDropBack: Forward-Consistent Stochastic Regularization for Deep Networks","created":"2024-11-16","cited_by_count":0,"area":null},{"id":"2602.09190","title":"Gradient Residual Connections","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.21819","title":"Ctrl-A: Control-Driven Online Data Augmentation","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2605.29525","title":"Learning to Perturb Hidden Representations for Generalizable Deep Learning","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.16761","title":"Dropout and Random Gradient Masking Are Asymptotically Equivalent in Large ResNets","created":"2026-07-18","cited_by_count":0,"area":null}],"next_cursor":null}