{"total":21,"rows":[{"id":"2305.09828","title":"Mimetic Initialization of Self-Attention Layers","created":"2023-05-16","cited_by_count":54,"area":null},{"id":"2203.09507","title":"Towards Data-Efficient Detection Transformers","created":"2022-03-17","cited_by_count":34,"area":null},{"id":"2203.07057","title":"Self-Promoted Supervision for Few-Shot Transformer","created":"2022-03-14","cited_by_count":22,"area":null},{"id":"2211.10686","title":"Spikeformer: A Novel Architecture for Training High-Performance Low-Latency Spiking Neural Network","created":"2022-11-19","cited_by_count":19,"area":null},{"id":"2208.14558","title":"Augraphy: A Data Augmentation Library for Document Images","created":"2022-08-30","cited_by_count":14,"area":null},{"id":"2408.00677","title":"Scaling Backwards: Minimal Synthetic Pre-training?","created":"2024-08-01","cited_by_count":14,"area":null},{"id":"2205.14986","title":"GMML is All you Need","created":"2022-05-30","cited_by_count":12,"area":null},{"id":"2307.14710","title":"Pre-training Vision Transformers with Very Limited Synthesized Images","created":"2023-07-27","cited_by_count":12,"area":null},{"id":"2202.07006","title":"A Survey of Visual Sensory Anomaly Detection","created":"2022-02-14","cited_by_count":11,"area":null},{"id":"2307.02100","title":"MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets","created":"2023-07-05","cited_by_count":9,"area":null},{"id":"2312.02843","title":"Are Vision Transformers More Data Hungry Than Newborn Visual Systems?","created":"2023-12-05","cited_by_count":7,"area":null},{"id":"2305.07931","title":"GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples","created":"2023-05-13","cited_by_count":4,"area":null},{"id":"2307.11550","title":"YOLOPose V2: Understanding and Improving Transformer-based 6D Pose Estimation","created":"2023-07-21","cited_by_count":3,"area":null},{"id":"2410.21329","title":"CloudCast -- Total Cloud Cover Nowcasting with Machine Learning","created":"2024-10-27","cited_by_count":3,"area":null},{"id":"2207.12318","title":"Action Quality Assessment using Transformers","created":"2022-07-20","cited_by_count":2,"area":null},{"id":"2307.04442","title":"Automatic diagnosis of knee osteoarthritis severity using Swin transformer","created":"2023-07-10","cited_by_count":2,"area":null},{"id":"2404.19289","title":"On Improving the Algorithm-, Model-, and Data- Efficiency of Self-Supervised Learning","created":"2024-04-30","cited_by_count":1,"area":null},{"id":"2512.14639","title":"AMD-HookNet++: Evolution of AMD-HookNet with Hybrid CNN-Transformer Feature Enhancement for Glacier Calving Front Segmentation","created":"2025-12-16","cited_by_count":1,"area":null},{"id":"2403.09579","title":"uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2601.14786","title":"Training-Efficient Text-to-Music Generation with State-Space Modeling","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2610.03772","title":"Energy Variation in Training Modern Computer Vision Architectures","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}