Zobrazeno 1 - 10
of 514
pro vyhledávání: '"Wang, Haoqi"'
Vision Transformer models trained on large-scale datasets, although effective, often exhibit artifacts in the patch token they extract. While such defects can be alleviated by re-training the entire model with additional classification tokens, the un
Externí odkaz:
http://arxiv.org/abs/2407.16826
We generalize the class vectors found in neural networks to linear subspaces (i.e.~points in the Grassmann manifold) and show that the Grassmann Class Representation (GCR) enables the simultaneous improvement in accuracy and feature transferability.
Externí odkaz:
http://arxiv.org/abs/2308.01547
Autor:
Zhang, Jingyang, Yang, Jingkang, Wang, Pengyun, Wang, Haoqi, Lin, Yueqian, Zhang, Haoran, Sun, Yiyou, Du, Xuefeng, Li, Yixuan, Liu, Ziwei, Chen, Yiran, Li, Hai
Out-of-Distribution (OOD) detection is critical for the reliable operation of open-world intelligent systems. Despite the emergence of an increasing number of OOD detection methods, the evaluation inconsistencies present challenges for tracking the p
Externí odkaz:
http://arxiv.org/abs/2306.09301
Autor:
Yang, Jingkang, Wang, Pengyun, Zou, Dejian, Zhou, Zitang, Ding, Kunyuan, Peng, Wenxuan, Wang, Haoqi, Chen, Guangyao, Li, Bo, Sun, Yiyou, Du, Xuefeng, Zhou, Kaiyang, Zhang, Wayne, Hendrycks, Dan, Li, Yixuan, Liu, Ziwei
Out-of-distribution (OOD) detection is vital to safety-critical machine learning applications and has thus been extensively studied, with a plethora of methods developed in the literature. However, the field currently lacks a unified, strictly formul
Externí odkaz:
http://arxiv.org/abs/2210.07242
Most of the existing Out-Of-Distribution (OOD) detection algorithms depend on single input source: the feature, the logit, or the softmax probability. However, the immense diversity of the OOD examples makes such methods fragile. There are OOD sample
Externí odkaz:
http://arxiv.org/abs/2203.10807
Publikováno v:
In Science of the Total Environment 10 November 2024 950
Publikováno v:
In Structural Safety November 2024 111
Autor:
Wang, Haoqi, Wang, Guangwei, Li, Hao, Leng, Jiewu, Lv, Lindong, Thomson, Vincent, Zhang, Yuyan, Li, Linli, Chen, Lucheng
Publikováno v:
In Advanced Engineering Informatics October 2024 62 Part C
Publikováno v:
In Cleaner Environmental Systems September 2024 14
Publikováno v:
In Journal of Water Process Engineering September 2024 66