Yichun Shi

Yichun Shi

Auto-generated profile, based on publicly available information

Yichun Shi

ByteDance Inc., United States of America

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
23 January 2018 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
YSYichun Shi
Yichun Shi
COCharles Otto
Charles Otto
AJAnil K. Jain
Anil K. Jain
Clustering face images according to their latent identity has two important applications: 1) grouping a collection of face images when no external labels are associated with images, and 2) indexing for efficient large scale face retrieval. The clustering problem is composed of two key parts: representation and similarity metric for face images, and choice of the partition algorithm. We first propose a representation based on ResNet, which has been shown to perform very well in image classification problems. Given this representation, we design a clustering algorithm, Conditional Pairwise Clustering (ConPaC), which directly estimates the adjacency matrix only based on the similarities between face images. This allows a dynamic selection of number of clusters and retains pairwise similarities between faces. ConPaC formulates the clustering problem as a Conditional Random Field model and uses Loopy Belief Propagation to find an approximate solution for maximizing the posterior probability of the adjacency matrix. Experimental results on two benchmark face datasets (LFW and IJB-B) show that ConPaC outperforms well known clustering algorithms such as k-means, spectral clustering, and approximate Rank-order. Additionally, our algorithm can naturally incorporate pairwise constraints to work in a semi-supervised way that leads to improved clustering performance. We also propose a k-NN variant of ConPaC, which has a linear time complexity given a k-NN graph, suitable for large datasets.

9 January 2023 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
LZLiling Zhang
Liling Zhang
XLXinyu Lei
Xinyu Lei
YSYichun Shi
Yichun Shi
HHHongyu Huang
Hongyu Huang
CCChao Chen
Chao Chen
Federated learning (FL) is a distributed machine learning (ML) technique that allows numerous Internet of Things (IoT) devices to jointly train an ML model using a centralized server for help. Local data never leaves each IoT device in FL, so the local data of IoT devices are protected. In FL, distributed IoT devices usually collect their local data independently, so the data set of each IoT device may naturally form a distinct source domain. In real-world applications, the model trained over multisource domains may have poor generalization performance on unseen target domains. To address this issue, we propose federated adversarial domain generalization (FedADG) to equip FL with domain generalization capability. FedADG employs the federated adversarial learning approach to measure and align the distributions among different source domains via matching each distribution to a reference distribution. The reference distribution is adaptively generated (by accommodating all source domains) to minimize the domain shift distance during alignment. Therefore, the learned feature representation tends to be universal, and, thus, it has good generalization performance over the unseen target domains while protecting local data privacy. Intensive experiments on various data sets demonstrate that FedADG has comparable performance with the state-of-the-art.

13 July 2024
Verified
Conference Paper
Open access
YXYou Xie
You Xie
HXHongyi Xu
Hongyi Xu
GSGuoxian Song
Guoxian Song
CWChao Wang
Chao Wang
YSYichun Shi
Yichun Shi
LLLinjie Luo
Linjie Luo
We propose X-Portrait, an innovative conditional diffusion model tailored for generating expressive and temporally coherent portrait animation. Specifically, given a single portrait as appearance reference, we aim to animate it with motion derived from a driving video, capturing both highly dynamic and subtle facial expressions along with wide-range head movements. As its core, we leverage the generative prior of a pre-trained diffusion model as the rendering backbone, while achieve fine-grained head pose and expression control with novel controlling signals within the framework of ControlNet. In contrast to conventional coarse explicit controls such as facial landmarks, our motion control module is learned to interpret the dynamics directly from the original driving RGB inputs. The motion accuracy is further enhanced with a patch-based local control module that effectively enhance the motion attention to small-scale nuances like eyeball positions. Notably, to mitigate the identity leakage from the driving signals, we train our motion control modules with scaling-augmented cross-identity images, ensuring maximized disentanglement from the appearance reference modules. Experimental results demonstrate the universal effectiveness of X-Portrait across a diverse range of facial portraits and expressive driving sequences, and showcase its proficiency in generating captivating portrait animations with consistently maintained identity characteristics.

6 February 2019 in IEEE Transactions on Biometrics, Behavior, and Identity Science
Verified
Journal Article
Closed access
YSYichun Shi
Yichun Shi
AJAnil K. Jain
Anil K. Jain

1 August 2023 in International Journal of Science and Engineering Applications
Verified
Journal Article
Open access
YSYichun Shi
Yichun Shi