“I had the pleasure of working with Lingfeng at Walmart (Sams Club). We partnered together to solve complex issues tied to inventory levels, item locations, and streamlining the associate experience. Enough can't be said about his passion for the people he leads, furthering computer vision within Walmart, and innovation. His deep technical knowledge and welcoming nature helped our Program deliver ambiguous, novel computer vision solutions. He has quickly become the subject matter expert for computer vision within the company, from discussing potential solutions with our CEO to delivering and scaling various proof of concepts. His leadership is represented by the engineers and data scientists who report to him. As a TPM, these technologists made my job easy. Each team member was passionate about the work they do, clearly communicated concerns, and were up to speed on the newest technologies. I would love to work with Lingfeng again in the future.”
About
Activity
-
Excited to share that Srini Venkatesan is joining PayPal as our new Chief Technology Officer (CTO) on June 24. Srini is a seasoned technologist and…
Excited to share that Srini Venkatesan is joining PayPal as our new Chief Technology Officer (CTO) on June 24. Srini is a seasoned technologist and…
Liked by Lingfeng Zhang
-
Our exit technology is making waves! Progressive Grocer has recognized Sam's Club with the 2024 GroceryTech Innovation Award for a Large Chain…
Our exit technology is making waves! Progressive Grocer has recognized Sam's Club with the 2024 GroceryTech Innovation Award for a Large Chain…
Liked by Lingfeng Zhang
-
I am thrilled to share that Sam's Club has been honored as the 2024 recipient of the GroceryTech Innovation Award for Large Chain Retailer by…
I am thrilled to share that Sam's Club has been honored as the 2024 recipient of the GroceryTech Innovation Award for Large Chain Retailer by…
Liked by Lingfeng Zhang
Experience & Education
Licenses & Certifications
Publications
-
Hierarchical multi-label classification using fully associative ensemble learning
Pattern Recognition
Traditional flat classification methods (e.g., binary or multi-class classification) neglect the structural information between different classes. In contrast, Hierarchical Multi-label Classification (HMC) considers the structural information embedded in the class hierarchy, and uses it to improve classification performance. In this paper, we propose a local hierarchical ensemble framework for HMC, Fully Associative Ensemble Learning (FAEL). We model the relationship between each class node’s…
Traditional flat classification methods (e.g., binary or multi-class classification) neglect the structural information between different classes. In contrast, Hierarchical Multi-label Classification (HMC) considers the structural information embedded in the class hierarchy, and uses it to improve classification performance. In this paper, we propose a local hierarchical ensemble framework for HMC, Fully Associative Ensemble Learning (FAEL). We model the relationship between each class node’s global prediction and the local predictions of all the class nodes as a multi-variable regression problem with Frobenius norm or l1 norm regularization. It can be extended using the kernel trick, which explores the complex correlation between global and local prediction. In addition, we introduce a binary constraint model to restrict the optimal weight matrix learning. The proposed models have been applied to image annotation and gene function prediction datasets with tree structured class hierarchy and large scale visual recognition dataset with Direct Acyclic Graph (DAG) structured class hierarchy. The experimental results indicate that our models achieve better performance when compared with other baseline methods.
Other authorsSee publication -
Local classifier chains for deep face recognition
International Joint Conference on Biometrics (IJCB)
This paper focuses on improving the performance of current convolutional neural networks in face recognition without changing the network architecture. We propose a hierarchical framework that builds chains of local binary neural networks after one global neural network over all the class labels, Local Classifier Chains based Convolutional Neural Networks (LCC-CNN). Two different criteria based on a similarity matrix and confusion matrix are introduced to select binary label pairs to create…
This paper focuses on improving the performance of current convolutional neural networks in face recognition without changing the network architecture. We propose a hierarchical framework that builds chains of local binary neural networks after one global neural network over all the class labels, Local Classifier Chains based Convolutional Neural Networks (LCC-CNN). Two different criteria based on a similarity matrix and confusion matrix are introduced to select binary label pairs to create local deep networks. To avoid error propagation, each testing sample travels through one global model and a local classifier chain to obtain its final prediction. The proposed framework has been evaluated with UHDB31 and CASIA-WebFace datasets. The experimental results indicate that our framework achieves better performance when compared with using only baseline methods as the global deep network. The accuracy is improved by 2.7% and 0.7% on the two datasets, respectively.
Other authorsSee publication -
Hierarchical Multi-Label Framework for Robust Face Recognition
In Proc. International Conference on Biometrics
In this paper, we propose a patch based face recognition framework. First, a face image is iteratively divided into multi-level patches and assigned hierarchical labels. Second, local classifiers are built to learn the local prediction of each patch. Third, the hierarchical relationships defined between local patches are used to obtain the global prediction of each patch. We develop three ways to learn the global prediction: majority voting, `1-regularized weighting, and decision rule. Last…
In this paper, we propose a patch based face recognition framework. First, a face image is iteratively divided into multi-level patches and assigned hierarchical labels. Second, local classifiers are built to learn the local prediction of each patch. Third, the hierarchical relationships defined between local patches are used to obtain the global prediction of each patch. We develop three ways to learn the global prediction: majority voting, `1-regularized weighting, and decision rule. Last, the global predictions of different levels are combined as the final prediction. Experimental results on different face recognition tasks demonstrate the effectiveness of our method.
Other authorsSee publication -
Fully Associative Ensemble Learning for Hierarchical Multi-Label Classification
In Proc. British Machine Vision Conference
In contrast to traditional flat classification problems (e.g., binary or multi-class classification), Hierarchical Multi-label Classification (HMC) takes into account the structural information embedded in the class hierarchy. In this paper, we propose a local hierarchical ensemble framework, Fully Associative Ensemble Learning (FAEL). We model the relationship between each node’s global prediction and the local predictions of all the nodes as a multi-variable regression problem. The simplest…
In contrast to traditional flat classification problems (e.g., binary or multi-class classification), Hierarchical Multi-label Classification (HMC) takes into account the structural information embedded in the class hierarchy. In this paper, we propose a local hierarchical ensemble framework, Fully Associative Ensemble Learning (FAEL). We model the relationship between each node’s global prediction and the local predictions of all the nodes as a multi-variable regression problem. The simplest version of our model leads to a ridge regression problem. It can be extended using the kernel trick, which explores the complex correlation between global and local prediction. In addition, we introduce a binary constraint model to restrict the optimal weight matrix learning. The proposed models have been applied to image annotation and gene function prediction datasets. The experimental results indicate that our models achieve better performance when compared with other baseline methods.
Other authorsSee publication
Languages
-
English
Professional working proficiency
-
Chinese
Native or bilingual proficiency
Recommendations received
1 person has recommended Lingfeng
Join now to viewMore activity by Lingfeng
-
Grocery Tech is happening now! Looking forward to connecting with retail leaders in the coming days and discussing how technology can revolutionize…
Grocery Tech is happening now! Looking forward to connecting with retail leaders in the coming days and discussing how technology can revolutionize…
Liked by Lingfeng Zhang
-
Had an incredible day at the Progressive Grocer conference in Dallas with Lingfeng Zhang! 🎉 Our Exit CV team for Sam's Club was honored with the…
Had an incredible day at the Progressive Grocer conference in Dallas with Lingfeng Zhang! 🎉 Our Exit CV team for Sam's Club was honored with the…
Liked by Lingfeng Zhang
-
I am thrilled to share that the AI-powered exit technology in Sam’s Club won the Innovation Award in Grocery Tech Conference. Mike Schubert and I…
I am thrilled to share that the AI-powered exit technology in Sam’s Club won the Innovation Award in Grocery Tech Conference. Mike Schubert and I…
Shared by Lingfeng Zhang
-
Congrats to Suresh Kumar for being honored among Gold House's A100 list, a recognition of the 100 most impactful Asian Pacific leaders in culture and…
Congrats to Suresh Kumar for being honored among Gold House's A100 list, a recognition of the 100 most impactful Asian Pacific leaders in culture and…
Liked by Lingfeng Zhang
-
20 years already?? Best part is the folks I get to work with every day.
20 years already?? Best part is the folks I get to work with every day.
Liked by Lingfeng Zhang
-
That was the best #Calliscan team I have ever participated in. Thank you all of you for good memories. #SRK #Samsung
That was the best #Calliscan team I have ever participated in. Thank you all of you for good memories. #SRK #Samsung
Liked by Lingfeng Zhang
-
Innovation is at the heart of what we do at Sam's Club. With AI-powered exit technology now in 20% of our clubs, we’re providing members across the…
Innovation is at the heart of what we do at Sam's Club. With AI-powered exit technology now in 20% of our clubs, we’re providing members across the…
Liked by Lingfeng Zhang
-
It is always a pleasure to visit our Technology team in India. I return full of energy and with a feeling of gratitude after seeing and listening to…
It is always a pleasure to visit our Technology team in India. I return full of energy and with a feeling of gratitude after seeing and listening to…
Liked by Lingfeng Zhang
-
🎉 Congratulations to Suresh Kumar, honored among Gold House's A100 list! As Walmart's tech strategist, Suresh drives innovation rooted in purpose…
🎉 Congratulations to Suresh Kumar, honored among Gold House's A100 list! As Walmart's tech strategist, Suresh drives innovation rooted in purpose…
Liked by Lingfeng Zhang
-
We are hiring at Sam's Tech.. Come join my team in leading the way in tailoring personalized experiences for our members. I have Senior Software…
We are hiring at Sam's Tech.. Come join my team in leading the way in tailoring personalized experiences for our members. I have Senior Software…
Liked by Lingfeng Zhang
-
Had a good time sharing some of my insights on various #cybersecurity incidents and takeaways at the InfraGard Houston Members Alliance Technology…
Had a good time sharing some of my insights on various #cybersecurity incidents and takeaways at the InfraGard Houston Members Alliance Technology…
Liked by Lingfeng Zhang
-
Had the privilege of speaking alongside Cheryl Ainoa at #TheMorningMeeting! And of course, we had a blast while doing it! It was amazing to…
Had the privilege of speaking alongside Cheryl Ainoa at #TheMorningMeeting! And of course, we had a blast while doing it! It was amazing to…
Liked by Lingfeng Zhang
People also viewed
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Lingfeng Zhang in United States
-
Lingfeng Zhang
-
Lingfeng Zhang
Information Security Analyst Intern at Non-profit Healthcare Organization
-
Lingfeng Zhang
Grad Teaching Assistant
-
Lingfeng Zhang
Attended Georgia Institute of Technology
13 others named Lingfeng Zhang in United States are on LinkedIn
See others named Lingfeng Zhang