Zobrazeno 1 - 10
of 944
pro vyhledávání: '"Xie, Di"'
The ability of gaze estimation models to generalize is often significantly hindered by various factors unrelated to gaze, especially when the training dataset is limited. Current strategies aim to address this challenge through different domain gener
Externí odkaz:
http://arxiv.org/abs/2411.08606
Data-Free Knowledge Distillation (DFKD) has shown great potential in creating a compact student model while alleviating the dependency on real training data by synthesizing surrogate data. However, prior arts are seldom discussed under distribution s
Externí odkaz:
http://arxiv.org/abs/2407.15155
Previous face forgery detection methods mainly focus on appearance features, which may be easily attacked by sophisticated manipulation. Considering the majority of current face manipulation methods generate fake faces based on a single frame, which
Externí odkaz:
http://arxiv.org/abs/2403.05172
Gaze estimation methods often experience significant performance degradation when evaluated across different domains, due to the domain gap between the testing and training data. Existing methods try to address this issue using various domain general
Externí odkaz:
http://arxiv.org/abs/2403.05124
Recently, arbitrary-scale point cloud upsampling mechanism became increasingly popular due to its efficiency and convenience for practical applications. To achieve this, most previous approaches formulate it as a problem of surface approximation and
Externí odkaz:
http://arxiv.org/abs/2403.05117
Modern deep neural networks (DNNs) are extremely powerful; however, this comes at the price of increased depth and having more parameters per layer, making their training and inference more computationally challenging. In an attempt to address this k
Externí odkaz:
http://arxiv.org/abs/2403.00258
Autor:
Chen, Weijie, Wang, Haoyu, Yang, Shicai, Zhang, Lei, Wei, Wei, Zhang, Yanning, Lin, Luojun, Xie, Di, Zhuang, Yueting
We do not pursue a novel method in this paper, but aim to study if a modern text-to-image diffusion model can tailor any task-adaptive image classifier across domains and categories. Existing domain adaptive image classification works exploit both so
Externí odkaz:
http://arxiv.org/abs/2310.16573
Publikováno v:
Liang you shipin ke-ji, Vol 32, Iss 5, Pp 160-168 (2024)
A preliminary study was conducted on the inactivation effects and mechanisms of spore inactivation of Aspergillus flavus and Aspergillus chevalieri spores, as well as the degradation of aflatoxins (AFs) and deoxynivalenol (DON) by ultraviolet combine
Externí odkaz:
https://doaj.org/article/d8f3b9cda6544df4b50c215b6a2d70b9
Iris presentation attack detection (PAD) has achieved great success under intra-domain settings but easily degrades on unseen domains. Conventional domain generalization methods mitigate the gap by learning domain-invariant features. However, they ig
Externí odkaz:
http://arxiv.org/abs/2305.12800
Most existing approaches for point cloud normal estimation aim to locally fit a geometric surface and calculate the normal from the fitted surface. Recently, learning-based methods have adopted a routine of predicting point-wise weights to solve the
Externí odkaz:
http://arxiv.org/abs/2303.17167