Zobrazeno 1 - 10
of 261
pro vyhledávání: '"Liu, Yuchi"'
This paper evaluates the generalization ability of classification models on out-of-distribution test sets without depending on ground truth labels. Common approaches often calculate an unsupervised metric related to a specific model property, like co
Externí odkaz:
http://arxiv.org/abs/2406.09257
Large language models (LLMs) have shown great progress in responding to user questions, allowing for a multitude of diverse applications. Yet, the quality of LLM outputs heavily depends on the prompt design, where a good prompt might enable the LLM t
Externí odkaz:
http://arxiv.org/abs/2405.20252
Model calibration aims to align confidence with prediction correctness. The Cross-Entropy (CE) loss is widely used for calibrator training, which enforces the model to increase confidence on the ground truth class. However, we find the CE loss has in
Externí odkaz:
http://arxiv.org/abs/2404.13016
Autor:
Hao, Susan, Shelby, Renee, Liu, Yuchi, Srinivasan, Hansa, Bhutani, Mukul, Ayan, Burcu Karagol, Poplin, Ryan, Poddar, Shivani, Laszlo, Sarah
Text-to-image (T2I) models have emerged as a significant advancement in generative AI; however, there exist safety concerns regarding their potential to produce harmful image outputs even when users input seemingly safe prompts. This phenomenon, wher
Externí odkaz:
http://arxiv.org/abs/2402.01787
Coronavirus 2019 has brought severe challenges to social stability and public health worldwide. One effective way of curbing the epidemic is to require people to wear masks in public places and monitor mask-wearing states by utilizing suitable automa
Externí odkaz:
http://arxiv.org/abs/2203.16506
This paper does not contain technical novelty but introduces our key discoveries in a data generation protocol, a database and insights. We aim to address the lack of large-scale datasets in micro-expression (MiE) recognition due to the prohibitive c
Externí odkaz:
http://arxiv.org/abs/2112.01730
Autor:
Yang, Hao, Jia, Weishang, Zhang, Jingfang, Liu, Yuchi, Wang, Zihao, Yang, Yaoyue, Feng, Lanxiang, Yan, Xinxiu, Li, Tao, Zou, Wei, Li, Jingze
Publikováno v:
In Journal of Colloid And Interface Science May 2024 661:870-878
Autor:
Zhao, Taotao, Liu, Yuchi, Shen, Chenyang, Liu, Gui, Yao, Jun, Qian, Xiaofeng, He, Qiang, Mei, Feifei, Meng, Deming, Guo, Xuefeng, Peng, Luming, Xue, Nianhua, Zhu, Yan, Zhou, Yuming, Ding, Weiping
Publikováno v:
In Applied Catalysis B: Environment and Energy 5 August 2024 350
Association, aiming to link bounding boxes of the same identity in a video sequence, is a central component in multi-object tracking (MOT). To train association modules, e.g., parametric networks, real video data are usually used. However, annotating
Externí odkaz:
http://arxiv.org/abs/2106.16100
Although deep face recognition benefits significantly from large-scale training data, a current bottleneck is the labelling cost. A feasible solution to this problem is semi-supervised learning, exploiting a small portion of labelled data and large a
Externí odkaz:
http://arxiv.org/abs/2105.04431