no code implementations • 7 Apr 2024 • Qingshan Hou, Shuai Cheng, Peng Cao, Jinzhu Yang, Xiaoli Liu, Osmar R. Zaiane, Yih Chung Tham
Nevertheless, the effectiveness of CL is highly dependent on the quality of the positive and negative sample pairs.
no code implementations • 13 Mar 2024 • Ang Li, Qiugen Xiao, Peng Cao, Jian Tang, Yi Yuan, Zijie Zhao, Xiaoyuan Chen, Liang Zhang, Xiangyang Li, Kaitong Yang, Weidong Guo, Yukang Gan, Xu Yu, Daniell Wang, Ying Shan
Using ChatGPT as a labeler to provide feedback on open-domain prompts in RLAIF training, we observe an increase in human evaluators' preference win ratio for model responses, but a decrease in evaluators' satisfaction rate.
3 code implementations • 23 Dec 2023 • Haonan Wang, Peng Cao, Xiaoli Liu, Jinzhu Yang, Osmar Zaiane
Hence, both modules establish a learnable connection to solve the semantic gaps between the encoder and the decoder, which leads to a high-performance segmentation model for medical images.
1 code implementation • 17 Jan 2023 • Qingshan Hou, Peng Cao, Jiaqi Wang, Xiaoli Liu, Jinzhu Yang, Osmar R. Zaiane
Most of the existing image enhancement methods mainly focus on improving the image quality by leveraging the guidance of high-quality images, which is difficult to be collected in medical applications.
1 code implementation • 11 Jan 2023 • Zhiqiang Shen, Peng Cao, Hua Yang, Xiaoli Liu, Jinzhu Yang, Osmar R. Zaiane
Combining the strengths of UMIX with CMT, UCMT can retain model disagreement and enhance the quality of pseudo labels for the co-training segmentation.
no code implementations • 2 Jan 2023 • Chiyu Zhang, Jun Yang, Zaiyan Dai, Peng Cao
In recent years, arbitrary image style transfer has attracted more and more attention.
no code implementations • 6 Dec 2022 • Hao He, Yuan Yuan, Ying-Cong Chen, Peng Cao, Dina Katabi
With the increasing popularity of telehealth, it becomes critical to ensure that basic physiological signals can be monitored accurately at home, with minimal patient overhead.
no code implementations • 30 Nov 2022 • GuanXiong Luo, Mengmeng Kuang, Peng Cao
The data consistency for the physical forward model is crucial in inverse problems, especially in MR imaging reconstruction.
1 code implementation • CVPR 2022 • Tianhong Li, Peng Cao, Yuan Yuan, Lijie Fan, Yuzhe Yang, Rogerio Feris, Piotr Indyk, Dina Katabi
This forces all classes, including minority classes, to maintain a uniform distribution in the feature space, improves class boundaries, and provides better generalization even in the presence of long-tail data.
Ranked #22 on Long-tail Learning on CIFAR-10-LT (ρ=100)
3 code implementations • 9 Sep 2021 • Haonan Wang, Peng Cao, Jiaqi Wang, Osmar R. Zaiane
Specifically, the CTrans module is an alternate of the U-Net skip connections, which consists of a sub-module to conduct the multi-scale Channel Cross fusion with Transformer (named CCT) and a sub-module Channel-wise Cross-Attention (named CCA) to guide the fused multi-scale channel-wise information to effectively connect to the decoder features for eliminating the ambiguity.
Ranked #2 on Medical Image Segmentation on GlaS (IoU metric)
no code implementations • 28 Aug 2020 • Weiwen Wu, Dianlin Hu, Chuang Niu, Lieza Vanden Broeke, Anthony P. H. Butler, Peng Cao, James Atlas, Alexander Chernoglazov, Varut Vardhanabhuti, Ge Wang
To address the image deblurring problem associated with the $L_2^2$-loss, we propose a general $L_p^p$-loss, $p>0$ Furthermore, the images from different energy bins share similar structures of the same object, the regularization characterizing correlations of different energy bins is incorporated into the $L_p^p$-loss function, which helps unify the deep learning based methods with traditional compressed sensing based methods.
no code implementations • ECCV 2020 • Xinwei Sun, Yilun Xu, Peng Cao, Yuqing Kong, Lingjing Hu, Shanghang Zhang, Yizhou Wang
In this paper, we propose a novel information-theoretic approach, namely \textbf{T}otal \textbf{C}orrelation \textbf{G}ain \textbf{M}aximization (TCGM), for semi-supervised multi-modal learning, which is endowed with promising properties: (i) it can utilize effectively the information across different modalities of unlabeled data points to facilitate training classifiers of each modality (ii) it has theoretical guarantee to identify Bayesian classifiers, i. e., the ground truth posteriors of all modalities.
1 code implementation • 18 Apr 2020 • Emre Aksan, Manuel Kaufmann, Peng Cao, Otmar Hilliges
We propose a novel Transformer-based architecture for the task of generative modelling of 3D human motion.
no code implementations • NeurIPS 2019 • Yilun Xu, Peng Cao, Yuqing Kong, Yizhou Wang
To the best of our knowledge, L_DMI is the first loss function that is provably robust to instance-independent label noise, regardless of noise pattern, and it can be applied to any existing classification neural networks straightforwardly without any auxiliary information.
Ranked #36 on Image Classification on Clothing1M (using extra training data)
2 code implementations • 8 Sep 2019 • Yilun Xu, Peng Cao, Yuqing Kong, Yizhou Wang
\emph{To the best of our knowledge, $\mathcal{L}_{DMI}$ is the first loss function that is provably robust to instance-independent label noise, regardless of noise pattern, and it can be applied to any existing classification neural networks straightforwardly without any auxiliary information}.
Ranked #36 on Image Classification on Clothing1M
1 code implementation • 3 Sep 2019 • GuanXiong Luo, Na Zhao, Wenhao Jiang, Edward S. Hui, Peng Cao
Purpose: To develop a deep learning-based Bayesian inference for MRI reconstruction.
1 code implementation • ICLR 2019 • Peng Cao, Yilun Xu, Yuqing Kong, Yizhou Wang
Furthermore, we devise an accurate data-crowds forecaster that employs both the data and the crowdsourced labels to forecast the ground truth.