Zobrazeno 1 - 10
of 176
pro vyhledávání: '"Guan, Qingji"'
Deep learning-based edge detectors heavily rely on pixel-wise labels which are often provided by multiple annotators. Existing methods fuse multiple annotations using a simple voting process, ignoring the inherent ambiguity of edges and labeling bias
Externí odkaz:
http://arxiv.org/abs/2303.11828
Convolutional neural networks have made significant progresses in edge detection by progressively exploring the context and semantic features. However, local details are gradually suppressed with the enlarging of receptive fields. Recently, vision tr
Externí odkaz:
http://arxiv.org/abs/2203.08566
As a fundamental building block in computer vision, edges can be categorised into four types according to the discontinuity in surface-Reflectance, Illumination, surface-Normal or Depth. While great progress has been made in detecting generic or indi
Externí odkaz:
http://arxiv.org/abs/2108.00616
This paper addresses semi-supervised semantic segmentation by exploiting a small set of images with pixel-level annotations (strong supervisions) and a large set of images with only image-level annotations (weak supervisions). Most existing approache
Externí odkaz:
http://arxiv.org/abs/2103.14242
Publikováno v:
In Knowledge-Based Systems 25 October 2023 278
Publikováno v:
In Image and Vision Computing September 2023 137
Autor:
Zhang, Runsheng, Huang, Yaping, Pu, Mengyang, Zhang, Jian, Guan, Qingji, Zou, Qi, Ling, Haibin
TThe goal of our work is to discover dominant objects in a very general setting where only a single unlabeled image is given. This is far more challenge than typical co-localization or weakly-supervised localization tasks. To tackle this problem, we
Externí odkaz:
http://arxiv.org/abs/1902.09968
This paper considers the task of thorax disease classification on chest X-ray images. Existing methods generally use the global image as input for network learning. Such a strategy is limited in two aspects. 1) A thorax disease usually happens in (sm
Externí odkaz:
http://arxiv.org/abs/1801.09927
Publikováno v:
Algorithms. May2023, Vol. 16 Issue 5, p239. 12p.
Publikováno v:
In Journal of Visual Communication and Image Representation October 2020 72