Zobrazeno 1 - 10
of 623
pro vyhledávání: '"Zhang, YiHeng"'
The emergence of text-to-image generation models has led to the recognition that image enhancement, performed as post-processing, would significantly improve the visual quality of the generated images. Exploring diffusion models to enhance the genera
Externí odkaz:
http://arxiv.org/abs/2409.07451
Texture surface anomaly detection finds widespread applications in industrial settings. However, existing methods often necessitate gathering numerous samples for model training. Moreover, they predominantly operate within a close-set detection frame
Externí odkaz:
http://arxiv.org/abs/2406.07333
This paper presents LogiCode, a novel framework that leverages Large Language Models (LLMs) for identifying logical anomalies in industrial settings, moving beyond traditional focus on structural inconsistencies. By harnessing LLMs for logical reason
Externí odkaz:
http://arxiv.org/abs/2406.04687
This study targets Multi-Lighting Image Anomaly Detection (MLIAD), where multiple lighting conditions are utilized to enhance imaging quality and anomaly detection performance. While numerous image anomaly detection methods have been proposed, they l
Externí odkaz:
http://arxiv.org/abs/2406.04573
Autor:
Zhou, Zhou, Zhang, Yiheng, Xie, Yingxin, Huang, Tian, Li, Zile, Chen, Peng, Lu, Yanqing, Yu, Shaohua, Zhang, Shuang, Zheng, Guoxing
Publikováno v:
Light Sci Appl 13, 242 (2024)
Conventional lens-based imaging techniques have long been limited to capturing only the intensity distribution of objects, resulting in the loss of other crucial dimensions such as spectral data. Here, we report a spectral lens that captures both spa
Externí odkaz:
http://arxiv.org/abs/2308.12782
The recent advances in deep learning predominantly construct models in their internal representations, and it is opaque to explain the rationale behind and decisions to human users. Such explainability is especially essential for domain adaptation, w
Externí odkaz:
http://arxiv.org/abs/2211.08249
Multi-scale learning frameworks have been regarded as a capable class of models to boost semantic segmentation. The problem nevertheless is not trivial especially for the real-world deployments, which often demand high efficiency in inference latency
Externí odkaz:
http://arxiv.org/abs/2207.13600
Autor:
Pan, Yingwei, Li, Yehao, Zhang, Yiheng, Cai, Qi, Long, Fuchen, Qiu, Zhaofan, Yao, Ting, Mei, Tao
This paper presents an overview and comparative analysis of our systems designed for the following two tracks in SAPIEN ManiSkill Challenge 2021: No Interaction Track: The No Interaction track targets for learning policies from pre-collected demonstr
Externí odkaz:
http://arxiv.org/abs/2206.06289
Autor:
Li, Xuemei, Xiao, Xi, Zhang, Yiheng, Long, Ruimin, Kankala, Ranjith Kumar, Wang, Shibin, Liu, Yuangang
Publikováno v:
In International Journal of Biological Macromolecules December 2024 282 Part 5
Autor:
Yang, Xiao, Qiang, Rong, Shao, Yulong, Xue, Rui, Wu, Xu, Zhang, Yiheng, Ren, Fangjie, Ding, Yuancheng, Niu, Weihao, Ma, Qian, Wang, Yahui
Publikováno v:
In Journal of Alloys and Compounds 5 November 2024 1004