no code implementations • 22 Jan 2024 • Ci-Siang Lin, Chien-Yi Wang, Yu-Chiang Frank Wang, Min-Hung Chen
In this way, SemPLeS can perform better semantic alignment between object regions and the associated class labels, resulting in desired pseudo masks for training the segmentation model.
1 code implementation • 12 Dec 2023 • I-Jieh Liu, Ci-Siang Lin, Fu-En Yang, Yu-Chiang Frank Wang
Nevertheless, it is still challenging for FL to deal with user heterogeneity in their local data distribution in the real-world FL scenario, and this issue becomes even more severe in multi-label image classification.
no code implementations • 9 Sep 2023 • Ci-Siang Lin, Min-Hung Chen, Yu-Chiang Frank Wang
Data collected from the real world typically exhibit long-tailed distributions, where frequent classes contain abundant data while rare ones have only a limited number of samples.
no code implementations • CVPR 2023 • Yuan-Yi Xu, Ci-Siang Lin, Yu-Chiang Frank Wang
Learning models trained on biased datasets tend to observe correlations between categorical and undesirable features, which result in degraded performances.
no code implementations • 27 Dec 2021 • Yuan-Chia Cheng, Ci-Siang Lin, Fu-En Yang, Yu-Chiang Frank Wang
Few-shot classification aims to carry out classification given only few labeled examples for the categories of interest.
no code implementations • 27 Dec 2021 • Zu-Yun Shiau, Wei-Wei Lin, Ci-Siang Lin, Yu-Chiang Frank Wang
How to handle domain shifts when recognizing or segmenting visual data across domains has been studied by learning and vision communities.
no code implementations • 21 Oct 2020 • Jia-Wei Yan, Ci-Siang Lin, Fu-En Yang, Yu-Jhe Li, Yu-Chiang Frank Wang
Learning interpretable and interpolatable latent representations has been an emerging research direction, allowing researchers to understand and utilize the derived latent space for further applications such as visual synthesis or recognition.
no code implementations • 19 Oct 2020 • Ci-Siang Lin, Yuan-Chia Cheng, Yu-Chiang Frank Wang
That is, while a number of labeled source-domain datasets are available, we do not have access to any target-domain training data.
Domain Generalization Generalizable Person Re-identification +1
no code implementations • ICCV 2019 • Yu-Jhe Li, Ci-Siang Lin, Yan-Bo Lin, Yu-Chiang Frank Wang
Person re-identification (re-ID) aims at recognizing the same person from images taken across different cameras.
Ranked #16 on Unsupervised Domain Adaptation on Market to Duke