{"total":33,"rows":[{"id":"2305.09828","title":"Mimetic Initialization of Self-Attention Layers","created":"2023-05-16","cited_by_count":54,"area":null},{"id":"2311.18823","title":"Initializing Models with Larger Ones","created":"2023-11-30","cited_by_count":39,"area":null},{"id":"2402.18153","title":"Diffusion-Based Neural Network Weights Generation","created":"2024-02-28","cited_by_count":39,"area":null},{"id":"2305.02279","title":"Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models","created":"2023-05-03","cited_by_count":24,"area":null},{"id":"2211.13955","title":"MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention","created":"2022-11-25","cited_by_count":20,"area":null},{"id":"2310.08910","title":"Scalarization for Multi-Task and Multi-Domain Learning at Scale","created":"2023-10-13","cited_by_count":19,"area":null},{"id":"2310.20704","title":"Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoders","created":"2023-10-31","cited_by_count":17,"area":null},{"id":"2406.09294","title":"You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning","created":"2024-06-13","cited_by_count":16,"area":null},{"id":"2403.10519","title":"Frozen Feature Augmentation for Few-Shot Image Classification","created":"2024-03-15","cited_by_count":13,"area":null},{"id":"2312.06733","title":"TULIP: Transformer for Upsampling of LiDAR Point Clouds","created":"2023-12-11","cited_by_count":12,"area":null},{"id":"2403.17409","title":"Neural Clustering based Visual Representation Learning","created":"2024-03-26","cited_by_count":12,"area":null},{"id":"2407.05388","title":"Forest2Seq: Revitalizing Order Prior for Sequential Indoor Scene Synthesis","created":"2024-07-07","cited_by_count":12,"area":null},{"id":"2304.05350","title":"Astroformer: More Data Might not be all you need for Classification","created":"2023-04-03","cited_by_count":6,"area":null},{"id":"2310.00377","title":"Mitigating the Effect of Incidental Correlations on Part-based Learning","created":"2023-09-30","cited_by_count":6,"area":null},{"id":"2401.12511","title":"Convolutional Initialization for Data-Efficient Vision Transformers","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2409.04411","title":"Approximating Metric Magnitude of Point Sets","created":"2024-09-06","cited_by_count":4,"area":null},{"id":"2410.11428","title":"CTA-Net: A CNN-Transformer Aggregation Network for Improving Multi-Scale Feature Extraction","created":"2024-10-15","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":"2405.12357","title":"Paired Conditional Generative Adversarial Network for Highly Accelerated Liver 4D MRI","created":"2024-05-20","cited_by_count":3,"area":null},{"id":"2409.05785","title":"NeurLZ: An Online Neural Learning-Based Method to Enhance Scientific Lossy Compression","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2409.19582","title":"Self-supervised Auxiliary Learning for Texture and Model-based Hybrid Robust and Fair Featuring in Face Analysis","created":"2024-09-29","cited_by_count":3,"area":null},{"id":"2509.08959","title":"CoSwin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-Scale Vision","created":"2025-09-10","cited_by_count":3,"area":null},{"id":"2403.15567","title":"Do not trust what you trust: Miscalibration in Semi-supervised Learning","created":"2024-03-22","cited_by_count":2,"area":null},{"id":"2410.03359","title":"An Enhanced Harmonic Densely Connected Hybrid Transformer Network Architecture for Chronic Wound Segmentation Utilising Multi-Colour Space Tensor Merging","created":"2024-10-04","cited_by_count":2,"area":null},{"id":"2210.14319","title":"Explicitly Increasing Input Information Density for Vision Transformers on Small Datasets","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2212.05677","title":"Masked autoencoders are effective solution to transformer data-hungry","created":"2022-12-12","cited_by_count":1,"area":null},{"id":"2501.06220","title":"Powerful Design of Small Vision Transformer on CIFAR10","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2508.04429","title":"Unmasking Interstitial Lung Diseases: Leveraging Masked Autoencoders for Diagnosis","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2306.09320","title":"Learnable Weight Initialization for Volumetric Medical Image Segmentation","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2309.13373","title":"Asca: less audio data is more insightful","created":"2023-09-23","cited_by_count":0,"area":null},{"id":"2410.01003","title":"Y-CA-Net: A Convolutional Attention Based Network for Volumetric Medical Image Segmentation","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2505.13137","title":"Learning to Adapt to Position Bias in Vision Transformer Classifiers","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2610.16147","title":"BARTER: Compact Dynamic Sparse Training with Standard Dense Kernels","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}