Zobrazeno 1 - 10
of 234
pro vyhledávání: '"Qi, Zhiquan"'
Publikováno v:
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. 2021. Pages 678-684
We propose an end-to-end-trainable feature augmentation module built for image classification that extracts and exploits multi-view local features to boost model performance. Different from using global average pooling (GAP) to extract vectorized fea
Externí odkaz:
http://arxiv.org/abs/2206.12943
Publikováno v:
In Journal of Radiation Research and Applied Sciences September 2024 17(3)
Visual anomaly detection is an important and challenging problem in the field of machine learning and computer vision. This problem has attracted a considerable amount of attention in relevant research communities. Especially in recent years, the dev
Externí odkaz:
http://arxiv.org/abs/2109.13157
Pixel-level road crack detection has always been a challenging task in intelligent transportation systems. Due to the external environments, such as weather, light, and other factors, pavement cracks often present low contrast, poor continuity, and d
Externí odkaz:
http://arxiv.org/abs/2109.05707
Publikováno v:
In Pattern Recognition July 2024 151
Numerous detection problems in computer vision, including road crack detection, suffer from exceedingly foreground-background imbalance. Fortunately, modification of loss function appears to solve this puzzle once and for all. In this paper, we propo
Externí odkaz:
http://arxiv.org/abs/2106.15510
Learning from label proportions (LLP) aims at learning an instance-level classifier with label proportions in grouped training data. Existing deep learning based LLP methods utilize end-to-end pipelines to obtain the proportional loss with Kullback-L
Externí odkaz:
http://arxiv.org/abs/2105.10635
Publikováno v:
Neurocomputing 2021
Automatic detecting anomalous regions in images of objects or textures without priors of the anomalies is challenging, especially when the anomalies appear in very small areas of the images, making difficult-to-detect visual variations, such as defec
Externí odkaz:
http://arxiv.org/abs/2012.07122
Publikováno v:
In Procedia Computer Science 2024 242:1193-1197
This paper develops a multi-task learning framework that attempts to incorporate the image structure knowledge to assist image inpainting, which is not well explored in previous works. The primary idea is to train a shared generator to simultaneously
Externí odkaz:
http://arxiv.org/abs/2002.04170