no code implementations • 23 Feb 2024 • Xin Yi, LinLin Wang, Xiaoling Wang, Liang He
In this paper, we propose fine-grained detoxification via instance-level prefixes (FGDILP) to mitigate toxic text without additional cost.
1 code implementation • CVPR 2023 • Simin Li, Shuing Zhang, Gujun Chen, Dong Wang, Pu Feng, Jiakai Wang, Aishan Liu, Xin Yi, Xianglong Liu
First, to benchmark attack naturalness, we contribute the first Physical Attack Naturalness (PAN) dataset with human rating and gaze.
no code implementations • 18 Mar 2023 • Yuntao Wang, Zirui Cheng, Xin Yi, Yan Kong, Xueyang Wang, Xuhai Xu, Yukang Yan, Chun Yu, Shwetak Patel, Yuanchun Shi
Modeling the trade-off of privacy preservation and machine recognition performance can guide future privacy-preserving computer vision systems using low-resolution image sensors.
no code implementations • 28 Apr 2021 • Xin Yi, Jiahao Wu, Bo Ma, Yangtong Ou, Longyao Liu
Object detection is widely studied in computer vision filed.
no code implementations • 19 Apr 2021 • Yulin Zhang, Bo Ma, Longyao Liu, Xin Yi
The one-shot Person Re-ID scenario faces two kinds of uncertainties when constructing the prediction model from $X$ to $Y$.
no code implementations • 6 Feb 2021 • Xin Yi, Bo Ma, Yulin Zhang, Longyao Liu, Jiahao Wu
To alleviate the intra-domain gap of the synthetic domain, we propose an intra-domain adaptation to align distributions of other subsets to the optimal subset by adversarial learning.
no code implementations • 30 Nov 2020 • Longyao Liu, Bo Ma, Yulin Zhang, Xin Yi, Haozhi Li
In this paper, we carefully analyze the characteristics of FSOD, and present that a general few-shot detector should consider the explicit decomposition of two subtasks, as well as leveraging information from both of them to enhance feature representations.
no code implementations • 14 Nov 2020 • Robert D. E. Henderson, Xin Yi, Scott J. Adams, Paul Babyn
Performance was similar for the set of 58 test images consisting of 2 or more catheters, with an AP of 0. 975 (0. 255-1. 000) for NGTs, 0. 997 (0. 009-1. 000) for ETTs, 0. 981 (0. 797-0. 998) for UACs, and 0. 937 (0. 689-0. 990) for UVCs.
1 code implementation • 9 Feb 2020 • Xin Yi, Scott J. Adams, Robert D. E. Henderson, Paul Babyn
Catheters are the second most common abnormal finding on radiographs.
1 code implementation • 29 Aug 2019 • Linjie Deng, Yanxiang Gong, Xinchen Lu, Xin Yi, Zheng Ma, Mei Xie
Recently, scene text recognition methods based on deep learning have sprung up in computer vision area.
1 code implementation • 19 Sep 2018 • Xin Yi, Ekta Walia, Paul Babyn
Generative adversarial networks have gained a lot of attention in the computer vision community due to their capability of data generation without explicitly modelling the probability density function.
1 code implementation • 4 Jun 2018 • Xin Yi, Scott Adams, Paul Babyn, Abdul Elnajmi
In this work, we proposed a simple way of synthesizing catheters on X-ray images and a scale recurrent network for catheter detection.
no code implementations • 10 Apr 2018 • Xin Yi, Ekta Walia, Paul Babyn
Melanoma is a curable aggressive skin cancer if detected early.
2 code implementations • 22 Aug 2017 • Xin Yi, Paul Babyn
Low Dose Computed Tomography (LDCT) has offered tremendous benefits in radiation restricted applications, but the quantum noise as resulted by the insufficient number of photons could potentially harm the diagnostic performance.