T
Tianyu Guo
Researcher at Peking University
Publications - 16
Citations - 1207
Tianyu Guo is an academic researcher from Peking University. The author has contributed to research in topics: Artificial neural network & Robustness (computer science). The author has an hindex of 6, co-authored 13 publications receiving 215 citations. Previous affiliations of Tianyu Guo include University of Sydney.
Papers
More filters
Posted Content
Pre-Trained Image Processing Transformer
Hanting Chen,Yunhe Wang,Tianyu Guo,Chang Xu,Yiping Deng,Zhenhua Liu,Siwei Ma,Chunjing Xu,Chao Xu,Wen Gao +9 more
TL;DR: To maximally excavate the capability of transformer, the IPT model is presented to utilize the well-known ImageNet benchmark for generating a large amount of corrupted image pairs and the contrastive learning is introduced for well adapting to different image processing tasks.
Proceedings ArticleDOI
Pre-Trained Image Processing Transformer
Hanting Chen,Yunhe Wang,Tianyu Guo,Chang Xu,Yiping Deng,Zhenhua Liu,Siwei Ma,Chunjing Xu,Chao Xu,Wen Gao +9 more
TL;DR: Hu et al. as discussed by the authors proposed a pre-trained image processing transformer (IPT) model for denoising, super-resolution and deraining tasks, which is trained on corrupted image pairs with multi-heads and multi-tails.
Proceedings Article
Reinforced Multi-Label Image Classification by Exploring Curriculum
TL;DR: A reinforced multi-label image classification approach imitating human behavior to label image from easy to complex is proposed, which allows a reinforcement learning agent to sequentially predict labels by fully exploiting image feature and previously predicted labels.
Journal ArticleDOI
Robust Student Network Learning
TL;DR: In this paper, the authors make the student network produce more confident predictions with the help of the teacher network, and analyze the lower bound of the perturbation that will destroy the confidence of the student networks.
Proceedings ArticleDOI
On Positive-Unlabeled Classification in GAN
TL;DR: In this paper, a new Positive-Unlabeled GAN (PUGAN) is proposed to stabilize the training of the discriminator in standard GANs, which can achieve comparable or even better performance than those sophisticated discriminator stabilization methods.