{"total":36,"rows":[{"id":"2105.07576","title":"Rethinking \"Batch\" in BatchNorm","created":"2021-05-17","cited_by_count":45,"area":null},{"id":"2110.00175","title":"DualNet: Continual Learning, Fast and Slow","created":"2021-10-01","cited_by_count":39,"area":null},{"id":"2405.11582","title":"SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization","created":"2024-05-19","cited_by_count":17,"area":null},{"id":"2210.05153","title":"Understanding the Failure of Batch Normalization for Transformers in NLP","created":"2022-10-11","cited_by_count":12,"area":null},{"id":"2107.02279","title":"Design Smells in Deep Learning Programs: An Empirical Study","created":"2021-07-05","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":"2302.06112","title":"How to Use Dropout Correctly on Residual Networks with Batch Normalization","created":"2023-02-13","cited_by_count":7,"area":null},{"id":"2106.10771","title":"Multirate Training of Neural Networks","created":"2021-06-20","cited_by_count":5,"area":null},{"id":"2106.00673","title":"Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks","created":"2021-06-01","cited_by_count":3,"area":null},{"id":"2205.15146","title":"Batch Normalization Is Blind to the First and Second Derivatives of the Loss","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2306.01001","title":"DiffLoad: Uncertainty Quantification in Electrical Load Forecasting with the Diffusion Model","created":"2023-05-31","cited_by_count":3,"area":null},{"id":"2402.16255","title":"Watch Your Head: Assembling Projection Heads to Save the Reliability of Federated Models","created":"2024-02-26","cited_by_count":3,"area":null},{"id":"2506.12738","title":"Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution","created":"2025-06-15","cited_by_count":3,"area":null},{"id":"2204.00694","title":"Testing Feedforward Neural Networks Training Programs","created":"2022-04-01","cited_by_count":2,"area":null},{"id":"2205.11702","title":"Functional Network: A Novel Framework for Interpretability of Deep Neural Networks","created":"2022-05-24","cited_by_count":2,"area":null},{"id":"2211.05762","title":"Efficient brain age prediction from 3D MRI volumes using 2D projections","created":"2022-11-10","cited_by_count":2,"area":null},{"id":"2212.10430","title":"Walking Noise: On Layer-Specific Robustness of Neural Architectures against Noisy Computations and Associated Characteristic Learning Dynamics","created":"2022-12-20","cited_by_count":2,"area":null},{"id":"2305.16179","title":"Dropout Drops Double Descent","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2409.00971","title":"Interpretable Convolutional SyncNet","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2206.00913","title":"Improving the Robustness and Generalization of Deep Neural Network with Confidence Threshold Reduction","created":"2022-06-02","cited_by_count":1,"area":null},{"id":"2209.13382","title":"Measuring Overfitting in Convolutional Neural Networks using Adversarial Perturbations and Label Noise","created":"2022-09-27","cited_by_count":1,"area":null},{"id":"2302.12378","title":"Cosmic Microwave Background Recovery: A Graph-Based Bayesian Convolutional Network Approach","created":"2023-02-24","cited_by_count":1,"area":null},{"id":"2306.16993","title":"Weight Compander: A Simple Weight Reparameterization for Regularization","created":"2023-06-29","cited_by_count":1,"area":null},{"id":"2310.19119","title":"Out-of-distribution Object Detection through Bayesian Uncertainty Estimation","created":"2023-10-29","cited_by_count":1,"area":null},{"id":"2209.02370","title":"Continual Learning, Fast and Slow","created":"2022-09-06","cited_by_count":0,"area":null},{"id":"2209.09649","title":"Predicting Mutual Funds' Performance using Deep Learning and Ensemble Techniques","created":"2022-09-18","cited_by_count":0,"area":null},{"id":"2210.09909","title":"Uncertainty estimation for out-of-distribution detection in computational histopathology","created":"2022-10-18","cited_by_count":0,"area":null},{"id":"2303.12653","title":"Robust Millimeter Beamforming via Self-Supervised Hybrid Deep Learning","created":"2023-03-09","cited_by_count":0,"area":null},{"id":"2305.13447","title":"Regularization Through Simultaneous Learning: A Case Study on Plant Classification","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2307.15069","title":"Combining transmission speckle photography and convolutional neural network for determination of fat content in cow's milk -- an exercise in classification of parameters of a complex suspension","created":"2023-07-08","cited_by_count":0,"area":null},{"id":"2308.13441","title":"Mesh-Wise Prediction of Demographic Composition from Satellite Images Using Multi-Head Convolutional Neural Network","created":"2023-08-25","cited_by_count":0,"area":null},{"id":"2409.16630","title":"Stochastic Subsampling With Average Pooling","created":"2024-09-25","cited_by_count":0,"area":null},{"id":"2411.15876","title":"DUA-D2C: Dynamic Uncertainty Aware Method for Overfitting Remediation in Deep Learning","created":"2024-11-24","cited_by_count":0,"area":null},{"id":"2609.32062","title":"Correcting the Dropout-LayerNorm Expectation Gap Improves Protein Structure Models","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.04518","title":"Length Generalization Needs Proper Regularization","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}