James Liang

James Liang

Auto-generated profile, based on publicly available information

James Liang

Rochester Institute of Technology, Rochester, New York, USA

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 October 2022
Verified
Book Chapter
Closed access
PDF file
ZCZhiyuan Cheng
Zhiyuan Cheng
JLJames Liang
James Liang
HCHongjun Choi
Hongjun Choi
GTGuanhong Tao
Guanhong Tao
ZCZhiwen Cao
Zhiwen Cao
XZXiangyu Zhang
Xiangyu Zhang

8 May 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
Dongfang LiuDongfang Liu
Dongfang Liu
JLJames Liang
James Liang
TGTony Geng
Tony Geng
ALAlexander Loui
Alexander Loui
Tianfei ZhouTianfei Zhou
Tianfei Zhou
Learning pyramidal feature representations is important for many dense prediction tasks ( e.g ., object detection, semantic segmentation) that demand multi-scale visual understanding. Feature Pyramid Network (FPN) is a well-known architecture for multi-scale feature learning, however, intrinsic weaknesses in feature extraction and fusion impede the production of informative features. This work addresses the weaknesses of FPN through a novel tripartite feature enhanced pyramid network (TFPN), with three distinct and effective designs. First, we develop a feature reference module with lateral connections to adaptively extract bottom-up features with richer details for feature pyramid construction. Second, we design a feature calibration module between adjacent layers that calibrates the upsampled features to be spatially aligned, allowing for feature fusion with accurate correspondences. Third, we introduce a feature feedback module in FPN, which creates a communication channel from the feature pyramid back to the bottom-up backbone and doubles the encoding capacity, enabling the entire architecture to generate incrementally more powerful representations. The TFPN is extensively evaluated over four popular dense prediction tasks, i.e ., object detection, instance segmentation, panoptic segmentation, and semantic segmentation. The results demonstrate that TFPN consistently and significantly outperforms the vanilla FPN. Our code is available at https://github.com/jamesliang819.

13 March 2025 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Closed access
XLXiang Liu
Xiang Liu
JLJames Liang
James Liang
JZJianwei Zhang
Jianwei Zhang
ZQZihan Qian
Zihan Qian
PXPhoebe Xing
Phoebe Xing
JZJunhan Zhao
Junhan Zhao

2 April 2023 in arXiv
Verified
Preprint
Open access
PDF file
ZCZhiyuan Cheng
Zhiyuan Cheng
JLJames Liang
James Liang
GTGuanhong Tao
Guanhong Tao
Dongfang LiuDongfang Liu
Dongfang Liu
XZXiangyu Zhang
Xiangyu Zhang
Monocular Depth Estimation (MDE) is a critical component in applications such as autonomous driving. There are various attacks against MDE networks. These attacks, especially the physical ones, pose a great threat to the security of such systems. Traditional adversarial training method requires ground-truth labels hence cannot be directly applied to self-supervised MDE that does not have ground-truth depth. Some self-supervised model hardening techniques (e.g., contrastive learning) ignore the domain knowledge of MDE and can hardly achieve optimal performance. In this work, we propose a novel adversarial training method for self-supervised MDE models based on view synthesis without using ground-truth depth. We improve adversarial robustness against physical-world attacks using L0-norm-bounded perturbation in training. We compare our method with supervised learning based and contrastive learning based methods that are tailored for MDE. Results on two representative MDE networks show that we achieve better robustness against various adversarial attacks with nearly no benign performance degradation.


16 November 2012 in Blood
Verified
Journal Article
Open access
DSDavid Simpson
David Simpson
JLJames Liang
James Liang
RHRoss Henderson
Ross Henderson
MHMerit Hanna
Merit Hanna
EMEileen Merriman
Eileen Merriman
Abstract 4049