{"total":24,"rows":[{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613,"area":null},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368,"area":null},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364,"area":null},{"id":"2103.07579","title":"Revisiting ResNets: Improved Training and Scaling Strategies","created":"2021-03-13","cited_by_count":158,"area":null},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107,"area":null},{"id":"2102.11273","title":"On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness","created":"2021-02-22","cited_by_count":97,"area":null},{"id":"2110.13771","title":"AugMax: Adversarial Composition of Random Augmentations for Robust Training","created":"2021-10-26","cited_by_count":90,"area":null},{"id":"2102.00084","title":"A linearized framework and a new benchmark for model selection for fine-tuning","created":"2021-01-29","cited_by_count":41,"area":null},{"id":"2104.01086","title":"Defending Against Image Corruptions Through Adversarial Augmentations","created":"2021-04-02","cited_by_count":28,"area":null},{"id":"2110.08890","title":"Network Augmentation for Tiny Deep Learning","created":"2021-10-17","cited_by_count":24,"area":null},{"id":"2205.04533","title":"How Does Frequency Bias Affect the Robustness of Neural Image Classifiers against Common Corruption and Adversarial Perturbations?","created":"2022-05-09","cited_by_count":11,"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":"2207.10341","title":"UFO: Unified Feature Optimization","created":"2022-07-21","cited_by_count":7,"area":null},{"id":"2106.03640","title":"Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training","created":"2021-06-07","cited_by_count":6,"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":"2110.10645","title":"Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs","created":"2021-10-20","cited_by_count":5,"area":null},{"id":"2209.09844","title":"Frequency Dropout: Feature-Level Regularization via Randomized Filtering","created":"2022-09-20","cited_by_count":2,"area":null},{"id":"2406.01494","title":"Robust Classification by Coupling Data Mollification with Label Smoothing","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2306.13586","title":"NetBooster: Empowering Tiny Deep Learning By Standing on the Shoulders of Deep Giants","created":"2023-06-23","cited_by_count":1,"area":null},{"id":"2103.07230","title":"Sequential Random Network for Fine-grained Image Classification","created":"2021-03-12","cited_by_count":0,"area":null},{"id":"2202.12818","title":"Improving generalization with synthetic training data for deep learning based quality inspection","created":"2022-02-25","cited_by_count":0,"area":null},{"id":"2206.05898","title":"Pixel to Binary Embedding Towards Robustness for CNNs","created":"2022-06-13","cited_by_count":0,"area":null},{"id":"2209.11356","title":"NasHD: Efficient ViT Architecture Performance Ranking using Hyperdimensional Computing","created":"2022-09-23","cited_by_count":0,"area":null},{"id":"2301.01343","title":"Explainability and Robustness of Deep Visual Classification Models","created":"2023-01-03","cited_by_count":0,"area":null}],"next_cursor":null}