Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Litong Feng"'
Autor:
Yajie Guan, Xiufang Cui, Di Chen, Wennan Su, Yao Zhao, Jian Li, Litong Feng, Xinyao Li, Guo Jin
Publikováno v:
Materials Today Communications. 35:106098
Publikováno v:
Materials Today Communications. 35:106207
Publikováno v:
Surface and Coatings Technology. 461:129447
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:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b2f72a7f2a4234a98667f874300003a7
Autor:
Yuzhi Zhao, Litong Feng, Yasar Abbas Ur Rehman, Lai-Man Po, Weifeng Ou, Zhang Yujia, Chang Zhou
Publikováno v:
IEEE Access, Vol 8, Pp 109758-109769 (2020)
In recent years, the angle-based softmax losses have significantly improved the performance of face recognition whereas these loss functions are all based on cosine logit. A potential weakness is that the nonlinearity of the cosine function may undes
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Current out-of-distribution (OOD) detection benchmarks are commonly built by defining one dataset as in-distribution (ID) and all others as OOD. However, these benchmarks unfortunately introduce some unwanted and impractical goals, e.g., to perfectly
Publikováno v:
Applied Surface Science. 593:153381
Publikováno v:
Materials Chemistry and Physics. 280:125756
Webly supervised learning becomes attractive recently for its efficiency in data expansion without expensive human labeling. However, adopting search queries or hashtags as web labels of images for training brings massive noise that degrades the perf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dd1c61322b422e656ba067ccb1496ea6
http://arxiv.org/abs/2010.05864
http://arxiv.org/abs/2010.05864
Publikováno v:
ACM Multimedia
Most advances in single image de-raining meet a key challenge, which is removing rain streaks with different scales and shapes while preserving image details. Existing single image de-raining approaches treat rain-streak removal as a process of pixel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::766d3586f88262ae3fb1440040201b04