1 code implementation • 16 Mar 2024 • Shichao Kan, Yuhai Deng, Yixiong Liang, Lihui Cen, Zhe Qu, Yigang Cen, Zhihai He
This paper presents a novel unsupervised deep metric learning approach, termed unsupervised collaborative metric learning with mixed-scale groups (MS-UGCML), devised to learn embeddings for objects of varying scales.
no code implementations • 9 Oct 2022 • Shichao Kan, Yixiong Liang, Min Li, Yigang Cen, Jianxin Wang, Zhihai He
To address this challenge, in this paper, we introduce a new method called coded residual transform (CRT) for deep metric learning to significantly improve its generalization capability.
1 code implementation • 11 Jul 2022 • Yixiong Liang, Shuo Feng, Qing Liu, Hulin Kuang, Jianfeng Liu, Liyan Liao, Yun Du, Jianxin Wang
To mimic these behaviors, we propose to explore contextual relationships to boost the performance of cervical abnormal cell detection.
1 code implementation • 30 Oct 2021 • Qing Liu, Haotian Liu, Wei Ke, Yixiong Liang
It reassembles features in a dimension-reduced feature space and simultaneously aggregates multiple features inside a large predefined region into multiple target features.
no code implementations • 3 Dec 2020 • Qing Liu, Haotian Liu, Yixiong Liang
In detail, for the first branch, we use a uniform sampler to sample pixels from predicted segmentation mask for Dice loss calculation, which leads to this branch naturally be biased in favour of large hard exudates as Dice loss generates larger cost on misidentification of large hard exudates than small hard exudates.
no code implementations • 14 Dec 2019 • Yao Xiang, Wanxin Sun, Changli Pan, Meng Yan, Zhihua Yin, Yixiong Liang
Our model achieves 97. 5% sensitivity (Sens) and 67. 8% specificity (Spec) on cervical cell image-level screening.
no code implementations • 5 Nov 2019 • Qing Liu, Beiji Zou, Yang Zhao, Yixiong Liang
To build connections among prediction branches, this paper introduces gradient boosting framework to deep classification model and proposes a gradient boosting network called BoostNet.
no code implementations • 11 Sep 2019 • Yukun Zhou, Zailiang Chen, Hailan Shen, Qing Liu, Rongchang Zhao, Yixiong Liang
In each branch, the input feature map is deduced into an enhancement map and a mask map, thereby highlighting the most discriminative parts or hiding them.
1 code implementation • 21 Dec 2018 • Yixiong Liang, Yuan Mao, Zhihong Tang, Meng Yan, Yuqian Zhao, Jianfeng Liu
Our method provides a flexible and efficient way to integrate complementary and redundant information from multiple multi-focus ultra HD unregistered images into a fused image that contains better description than any of the individual input images.
1 code implementation • 30 Oct 2018 • Yixiong Liang, Yuan Mao, Jiazhi Xia, Yao Xiang, Jianfeng Liu
Specifically, we propose a scale-invariant structure saliency selection scheme based on the difference-of-Gaussian (DoG) pyramid of images to build the weights or activity map.
1 code implementation • 14 Oct 2018 • Yixiong Liang, Zhihong Tang, Meng Yan, Jialin Chen, Qing Liu, Yao Xiang
In this paper we propose an efficient CNN-based object detection methods for cervical cancer cells/clumps detection.
no code implementations • 6 Mar 2018 • Rui Kang, Yixiong Liang, Chunyan Lian, Yuan Mao
The urine sediment analysis of particles in microscopic images can assist physicians in evaluating patients with renal and urinary tract diseases.
no code implementations • 14 Feb 2011 • Yixiong Liang, Lei Wang, Shenghui Liao, Beiji Zou
There is an increasing use of some imperceivable and redundant local features for face recognition.
no code implementations • 14 Feb 2011 • Yixiong Liang, Lei Wang, Yao Xiang, Beiji Zou
Inspired by biological vision systems, the over-complete local features with huge cardinality are increasingly used for face recognition during the last decades.