{"total":31,"rows":[{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135,"area":null},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764,"area":null},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419,"area":null},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338,"area":null},{"id":"2103.01988","title":"Self-supervised Pretraining of Visual Features in the Wild","created":"2021-03-02","cited_by_count":198,"area":null},{"id":"2103.05445","title":"Pixel-wise Anomaly Detection in Complex Driving Scenes","created":"2021-03-09","cited_by_count":109,"area":null},{"id":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84,"area":null},{"id":"2202.08360","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","created":"2022-02-16","cited_by_count":80,"area":null},{"id":"2103.03936","title":"Pufferfish: Communication-efficient Models At No Extra Cost","created":"2021-03-05","cited_by_count":61,"area":null},{"id":"2109.05472","title":"Compute and Energy Consumption Trends in Deep Learning Inference","created":"2021-09-12","cited_by_count":61,"area":null},{"id":"2106.14568","title":"Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity","created":"2021-06-28","cited_by_count":44,"area":null},{"id":"2102.07870","title":"Momentum Residual Neural Networks","created":"2021-02-15","cited_by_count":37,"area":null},{"id":"2104.03841","title":"ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition","created":"2021-04-08","cited_by_count":29,"area":null},{"id":"2104.15129","title":"Stealthy Backdoors as Compression Artifacts","created":"2021-04-30","cited_by_count":18,"area":null},{"id":"2108.10346","title":"Explaining Bayesian Neural Networks","created":"2021-08-23","cited_by_count":18,"area":null},{"id":"2107.01057","title":"Backward-Compatible Prediction Updates: A Probabilistic Approach","created":"2021-07-02","cited_by_count":14,"area":null},{"id":"2108.09976","title":"Revealing the Distributional Vulnerability of Discriminators by Implicit Generators","created":"2021-08-23","cited_by_count":10,"area":null},{"id":"2212.05813","title":"KonX: Cross-Resolution Image Quality Assessment","created":"2022-12-12","cited_by_count":9,"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":"2511.18452","title":"NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering","created":"2025-11-23","cited_by_count":6,"area":null},{"id":"2106.02288","title":"Tackling the Background Bias in Sparse Object Detection via Cropped Windows","created":"2021-06-04","cited_by_count":5,"area":null},{"id":"2212.05611","title":"Accelerating Self-Supervised Learning via Efficient Training Strategies","created":"2022-12-11","cited_by_count":5,"area":null},{"id":"2101.04293","title":"Estimating Galactic Distances From Images Using Self-supervised Representation Learning","created":"2021-01-12","cited_by_count":4,"area":null},{"id":"2202.03238","title":"Towards an Analytical Definition of Sufficient Data","created":"2022-02-07","cited_by_count":3,"area":null},{"id":"2103.01644","title":"Exploiting latent representation of sparse semantic layers for improved short-term motion prediction with Capsule Networks","created":"2021-03-02","cited_by_count":2,"area":null},{"id":"2110.05324","title":"Learnable Adaptive Cosine Estimator (LACE) for Image Classification","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2202.00198","title":"Recognition-Aware Learned Image Compression","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2103.03912","title":"Multi-modal anticipation of stochastic trajectories in a dynamic environment with Conditional Variational Autoencoders","created":"2021-03-05","cited_by_count":1,"area":null},{"id":"2105.09464","title":"Content-Augmented Feature Pyramid Network with Light Linear Spatial Transformers for Object Detection","created":"2021-05-20","cited_by_count":1,"area":null},{"id":"2201.07894","title":"Enhanced Performance of Pre-Trained Networks by Matched Augmentation Distributions","created":"2022-01-19","cited_by_count":0,"area":null},{"id":"2212.03421","title":"Capturing the Flow of Art History","created":"2022-12-07","cited_by_count":0,"area":null}],"next_cursor":null}