Search Results for author: Kai Jin

Found 6 papers, 0 papers with code

Low-Complexity SVM Signal Recovery in Bandwidth-Limited 100Gb/s PAM4 PON Upstream

no code implementations4 Jul 2024 Liyan Wu, Yanlu Huang, Kai Jin, Shangya Han, Kun Xu, Yanni Ou

We proposed a low-complexity SVM-based signal recovery algorithm and evaluated it in 100G-PON with 25G-class devices.

LUT-boosted CDR and Equalization for Burst-mode 50/100 Gbit/s Bandwidth-limited Flexible PON

no code implementations28 Jun 2024 Yanlu Huang, Liyan Wu, Shangya Han, Kai Jin, Kun Xu, Yanni Ou

We proposed and experimentally demonstrated a look-up table boosted fast CDR and equalization scheme for the burst-mode 50/100 Gbps bandwidth-limited flexible PON, requiring no preamble for convergence and achieved the same bit error rate performance as in the case of long preambles.

Masked Contrastive Reconstruction for Cross-modal Medical Image-Report Retrieval

no code implementations26 Dec 2023 Zeqiang Wei, Kai Jin, Xiuzhuang Zhou

However, due to task competition and information interference caused by significant differences between the inputs of the two proxy tasks, the effectiveness of representation learning for intra-modal and cross-modal features is limited.

Contrastive Learning Cross-Modal Retrieval +2

Enhancing Point Annotations with Superpixel and Confidence Learning Guided for Improving Semi-Supervised OCT Fluid Segmentation

no code implementations5 Jun 2023 Tengjin Weng, Yang shen, Kai Jin, Zhiming Cheng, Yunxiang Li, Gewen Zhang, Shuai Wang, Yaqi Wang

Specifically, we use points to annotate fluid regions in unlabeled OCT images and the Superpixel-Guided Pseudo-Label Generation (SGPLG) module generates pseudo-labels and pixel-level label trust maps from the point annotations.

Denoising Pseudo Label +1

Dispensed Transformer Network for Unsupervised Domain Adaptation

no code implementations28 Oct 2021 Yunxiang Li, Jingxiong Li, Ruilong Dan, Shuai Wang, Kai Jin, Guodong Zeng, Jun Wang, Xiangji Pan, Qianni Zhang, Huiyu Zhou, Qun Jin, Li Wang, Yaqi Wang

To mitigate this problem, a novel unsupervised domain adaptation (UDA) method named dispensed Transformer network (DTNet) is introduced in this paper.

Unsupervised Domain Adaptation

DeepTracker: Visualizing the Training Process of Convolutional Neural Networks

no code implementations26 Aug 2018 Dongyu Liu, Weiwei Cui, Kai Jin, YuXiao Guo, Huamin Qu

To bridge this gap and help domain experts with their training tasks in a practical environment, we propose a visual analytics system, DeepTracker, to facilitate the exploration of the rich dynamics of CNN training processes and to identify the unusual patterns that are hidden behind the huge amount of training log.

Cannot find the paper you are looking for? You can Submit a new open access paper.