会员服务
掩码自编码MAE
AFFMAE: Scalable and Efficient Vision Pretraining for Desktop Graphics Cards
Arxiv
0+阅读 · 2月18日
Benchmarking Self-Supervised Models for Cardiac Ultrasound View Classification
Arxiv
0+阅读 · 2月17日
Knowledge-Guided Masked Autoencoder with Linear Spectral Mixing and Spectral-Angle-Aware Reconstruction
Arxiv
0+阅读 · 2月10日
SleepMaMi: A Universal Sleep Foundation Model for Integrating Macro- and Micro-structures
Arxiv
0+阅读 · 2月7日
Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces
Arxiv
0+阅读 · 2月11日
Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces
Arxiv
0+阅读 · 2月10日
Out of the box age estimation through facial imagery: A Comprehensive Benchmark of Vision-Language Models vs. out-of-the-box Traditional Architectures
Arxiv
0+阅读 · 2月11日
Learning Probabilities of Causation with Mask-Augmented Data
Arxiv
0+阅读 · 2月10日
Early warning of Mpox outbreaks in U.S. jurisdictions using Lasso Vector Autoregression models with cross-jurisdictional lags
Arxiv
0+阅读 · 2月5日
PuYun-LDM: A Latent Diffusion Model for High-Resolution Ensemble Weather Forecasts
Arxiv
0+阅读 · 2月12日
PuYun-LDM: A Latent Diffusion Model for High-Resolution Ensemble Weather Forecasts
Arxiv
0+阅读 · 2月13日
Viewpoint Matters: Dynamically Optimizing Viewpoints with Masked Autoencoder for Visual Manipulation
Arxiv
0+阅读 · 2月4日
Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces
Arxiv
0+阅读 · 1月31日
Robust Representation Learning in Masked Autoencoders
Arxiv
0+阅读 · 2月3日
Reducing Simulation Dependence in Neutrino Telescopes with Masked Point Transformers
Arxiv
0+阅读 · 1月25日
参考链接
微信扫码咨询专知VIP会员
Top