Výsledky vyhledávání

Report

Masked Angle-Aware Autoencoder for Remote Sensing Images

Autor: Li, Zhihao, Hou, Biao, Ma, Siteng, Wu, Zitong, Guo, Xianpeng, Ren, Bo, Jiao, Licheng

To overcome the inherent domain gap between remote sensing (RS) images and natural images, some self-supervised representation learning methods have made promising progress. However, they have overlooked the diverse angles present in RS objects. This

Externí odkaz: http://arxiv.org/abs/2408.01946

Zobrazit plný text záznamu

Report

Breaking the Barrier: Selective Uncertainty-based Active Learning for Medical Image Segmentation

Autor: Ma, Siteng, Wu, Haochang, Lawlor, Aonghus, Dong, Ruihai

Active learning (AL) has found wide applications in medical image segmentation, aiming to alleviate the annotation workload and enhance performance. Conventional uncertainty-based AL methods, such as entropy and Bayesian, often rely on an aggregate o

Externí odkaz: http://arxiv.org/abs/2401.16298

Zobrazit plný text záznamu

Report

Adaptive Nonlinear Latent Transformation for Conditional Face Editing

Autor: Huang, Zhizhong, Ma, Siteng, Zhang, Junping, Shan, Hongming

Recent works for face editing usually manipulate the latent space of StyleGAN via the linear semantic directions. However, they usually suffer from the entanglement of facial attributes, need to tune the optimal editing strength, and are limited to b

Externí odkaz: http://arxiv.org/abs/2307.07790

Zobrazit plný text záznamu