Yuewei Lin

Yuewei Lin

Auto-generated profile, based on publicly available information

Yuewei Lin

Brookhaven National Laboratory

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
4 October 2017 in The Journal of Physical Chemistry Letters
Verified
Journal Article
Closed access
JTJanis Timoshenko
Janis Timoshenko
DLDeyu Lu
Deyu Lu
YLYuewei Lin
Yuewei Lin
AFAnatoly I. Frenkel
Anatoly I. Frenkel

31 July 2019 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
ZZZheng Zhang
Zheng Zhang
QZQin Zou
Qin Zou
YLYuewei Lin
Yuewei Lin
LCLong Chen
Long Chen
SWSong Wang
Song Wang
Hash coding has been widely used in the approximate nearest neighbor search for large-scale image retrieval. Recently, many deep hashing methods have been proposed and shown largely improved performance over traditional feature-learning methods. Most of these methods examine the pairwise similarity on the semantic-level labels, where the pairwise similarity is generally defined in a hard-assignment way. That is, the pairwise similarity is ‘1’ if they share no less than one class label and ‘0’ if they do not share any. However, such similarity definition cannot reflect the similarity ranking for pairwise images that hold multiple labels. In this paper, an improved deep hashing method is proposed to enhance the ability of multi-label image retrieval. We introduce a pairwise quantified similarity calculated on the normalized semantic labels. Based on this, we divide the pairwise similarity into two situations -- ‘hard similarity’ and ‘soft similarity’, where cross-entropy loss and mean square error loss are adapted respectively for more robust feature learning and hash coding. Experiments on three popular datasets demonstrate that, the proposed method outperforms the competing methods and achieves the state-of-the-art performance in multi-label image retrieval.

25 March 2025 in IEEE Access
Verified
Journal Article
Open access
ILImran Latif
Imran Latif
ANAlex C. Newkirk
Alex C. Newkirk
MCMatthew R. Carbone
Matthew R. Carbone
Arslan MunirArslan Munir
Arslan Munir
YLYuewei Lin
Yuewei Lin
ZDZhihua Dong
Zhihua Dong
The expansion of artificial intelligence (AI) applications has driven substantial investment in computational infrastructure, especially by cloud computing providers. Quantifying the energy footprint of this infrastructure requires models parameterized by the power demand of AI hardware during training. In this work, we measured the instantaneous power draw of an 8-GPU NVIDIA H100 HGX node during the training of open-source image classifier (ResNet) and large-language models (Llama2-13b).We characterize power demand for a single node configuration, providing foundational data for future multi-node studies. The maximum observed power draw was approximately 8.4 kW, 18% lower than the manufacturer-rated 10.2 kW, even with GPUs near full utilization. Holding model architecture constant, increasing batch size from 512 to 4096 images for ResNet reduced total training energy consumption by a factor of 4. These findings can inform capacity planning for data center operators and energy use estimates by researchers. Future work will investigate the impact of cooling technology and carbon-aware scheduling on AI workload energy consumption.

29 May 2012 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YLYuewei Lin
Yuewei Lin
YTYuan Yan Tang
Yuan Yan Tang
BFBin Fang
Bin Fang
ZSZhaowei Shang
Zhaowei Shang
YHYonghui Huang
Yonghui Huang
SWSong Wang
Song Wang
This paper introduces a new computational visual-attention model for static and dynamic saliency maps. First, we use the Earth Mover's Distance (EMD) to measure the center-surround difference in the receptive field, instead of using the Difference-of-Gaussian filter that is widely used in many previous visual-attention models. Second, we propose to take two steps of biologically inspired nonlinear operations for combining different features: combining subsets of basic features into a set of super features using the Lm-norm and then combining the super features using the Winner-Take-All mechanism. Third, we extend the proposed model to construct dynamic saliency maps from videos by using EMD for computing the center-surround difference in the spatiotemporal receptive field. We evaluate the performance of the proposed model on both static image data and video data. Comparison results show that the proposed model outperforms several existing models under a unified evaluation setting.

8 February 2016 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Open access
YLYuewei Lin
Yuewei Lin
YTYan Tong
Yan Tong
YCYu Cao
Yu Cao
YZYoujie Zhou
Youjie Zhou
SWSong Wang
Song Wang
Motion is one of the most important cues to separate foreground objects from the background in a video. Using a stationary camera, it is usually assumed that the background is static, while the foreground objects are moving most of the time. However, in practice, the foreground objects may show infrequent motions, such as abandoned objects and sleeping persons. Meanwhile, the background may contain frequent local motions, such as waving trees and/or grass. Such complexities may prevent the existing background subtraction algorithms from correctly identifying the foreground objects. In this paper, we propose a new approach that can detect the foreground objects with frequent and/or infrequent motions. Specifically, we use a visual-attention mechanism to infer a complete background from a subset of frames and then propagate it to the other frames for accurate background subtraction. Furthermore, we develop a feature-matching-based local motion stabilization algorithm to identify frequent local motions in the background for reducing false positives in the detected foreground. The proposed approach is fully unsupervised, without using any supervised learning for object detection and tracking. Extensive experiments on a large number of videos have demonstrated that the proposed approach outperforms the state-of-the-art motion detection and background subtraction methods in comparison.

29 May 2024 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
Xi YuXi Yu
Xi Yu
HTHuan-Hsin Tseng
Huan-Hsin Tseng
SYShinjae Yoo
Shinjae Yoo
HLHaibin Ling
Haibin Ling
YLYuewei Lin
Yuewei Lin
Domain Generalization (DG) aims to learn a generalizable model on the unseen target domain by only training on the multiple observed source domains. Although a variety of DG methods have focused on extracting domain-invariant features, the domain-specific class-relevant features have attracted attention and been argued to benefit generalization to the unseen target domain. To take into account the class-relevant domain-specific information, in this paper we propose an Information theory iNspired diSentanglement and pURification modEl (INSURE) to explicitly disentangle the latent features to obtain sufficient and compact (necessary) class-relevant feature for generalization to the unseen domain. Specifically, we first propose an information theory inspired loss function to ensure the disentangled class-relevant features contain sufficient class label information and the other disentangled auxiliary feature has sufficient domain information. We further propose a paired purification loss function to let the auxiliary feature discard all the class-relevant information and thus the class-relevant feature will contain sufficient and compact (necessary) class-relevant information. Moreover, instead of using multiple encoders, we propose to use a learnable binary mask as our disentangler to make the disentanglement more efficient and make the disentangled features complementary to each other. We conduct extensive experiments on five widely used DG benchmark datasets including PACS, VLCS, OfficeHome, TerraIncognita, and DomainNet. The proposed INSURE achieves state-of-the-art performance. We also empirically show that domain-specific class-relevant features are beneficial for domain generalization. The code is available at https://github.com/yuxi120407/INSURE.