Junsong Yuan
University at Buffalo
481 Papers
1.8K Citations
Junsong Yuan is an academic researcher from University at Buffalo. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 59, co-authored 401 publications. Previous affiliations of Junsong Yuan include Zhejiang University & Northwestern University.
Chat about Author
Papers
Federated Learning With Privacy-Preserving Ensemble Attention Distillation
Xuan Gong,Liangchen Song,Rishi Vedula,Abhishek Sharma,Meng Zheng,Benjamin Planche,Arun Innanje,Terrence Chen,Junsong Yuan,David Doermann,Ziyan Wu +10 more
TL;DR: This work proposes a privacy-preserving FL framework leveraging unlabeled public data for one-way offline knowledge distillation in this work and achieves very competitive performance with more robust privacy preservation based on extensive experiments on image classification, segmentation, and reconstruction tasks.
HOPE: Hierarchical Object Prototype Encoding for Efficient Object Instance Search in Videos
Tan Yu,Yuwei Wu,Junsong Yuan +2 more
- 01 Jul 2017
TL;DR: This paper presents a simple yet effective hierarchical object prototype encoding (HOPE) model to accelerate the object instance search without sacrificing accuracy, which exploits both the spatial and temporal self-similarity property existing in object proposals generated from video frames.
Mining Visual Collocation Patterns via Self-Supervised Subspace Learning
Junsong Yuan,Ying Wu +1 more
- 01 Apr 2012
TL;DR: The novelty of this work lies in a principled solution to the discovery of visual collocation patterns based on frequent itemset mining and a self-supervised subspace learning method to refine the visual codebook by feeding back discovered patterns via sub space learning.
15
•Proceedings Article
Rethinking Soft Labels for Knowledge Distillation: A Bias–Variance Tradeoff Perspective
Helong Zhou,Liangchen Song,Jiajie Chen,Ye Zhou,Guoli Wang,Junsong Yuan,Qian Zhang +6 more
- 03 May 2021
TL;DR: In this article, the bias-variance tradeoff brought by distillation with soft labels is investigated and weighted soft labels are proposed to help the network adaptively handle the sample-wise bias variance tradeoff.
15
Quantized fuzzy LBP for face recognition
Jianfeng Ren,Xudong Jiang,Junsong Yuan +2 more
- 19 Apr 2015
TL;DR: This work proposes to determine the fuzzy membership function by its sign only, and shows that this approach is more robust to noise, and demonstrates a superior performance to FLBP and many other LBP variants.
14