Sifei Liu

Sifei Liu

Auto-generated profile, based on publicly available information

Sifei Liu

NVIDIA, Santa Clara, USA

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
6 October 2018
Verified
Book Chapter
Closed access
PDF file
SLSifei Liu
Sifei Liu
GZGuangyu Zhong
Guangyu Zhong
SMShalini De Mello
Shalini De Mello
JGJinwei Gu
Jinwei Gu
VJVarun Jampani
Varun Jampani
JKJan Kautz
Jan Kautz

24 March 2022 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
TXTaihong Xiao
Taihong Xiao
SLSifei Liu
Sifei Liu
SMShalini De Mello
Shalini De Mello
ZYZhiding Yu
Zhiding Yu
JKJan Kautz
Jan Kautz
MYMing Yang
Ming Yang

3 December 2024
Verified
Conference Paper
Open access
CLChao Liu
Chao Liu
WNWeili Nie
Weili Nie
SLSifei Liu
Sifei Liu
ABAbhishek Badki
Abhishek Badki
HSHang Su
Hang Su
AVArash Vahdat
Arash Vahdat


18 July 2022 in arXiv
Verified
Preprint
Open access
PDF file
JXJiarui Xu
Jiarui Xu
SMShalini De Mello
Shalini De Mello
SLSifei Liu
Sifei Liu
WBWonmin Byeon
Wonmin Byeon
TBThomas Breuel
Thomas Breuel
XWXiaolong Wang
Xiaolong Wang
Grouping and recognition are important components of visual scene understanding, e.g., for object detection and semantic segmentation. With end-to-end deep learning systems, grouping of image regions usually happens implicitly via top-down supervision from pixel-level recognition labels. Instead, in this paper, we propose to bring back the grouping mechanism into deep networks, which allows semantic segments to emerge automatically with only text supervision. We propose a hierarchical Grouping Vision Transformer (GroupViT), which goes beyond the regular grid structure representation and learns to group image regions into progressively larger arbitrary-shaped segments. We train GroupViT jointly with a text encoder on a large-scale image-text dataset via contrastive losses. With only text supervision and without any pixel-level annotations, GroupViT learns to group together semantic regions and successfully transfers to the task of semantic segmentation in a zero-shot manner, i.e., without any further fine-tuning. It achieves a zero-shot accuracy of 52.3% mIoU on the PASCAL VOC 2012 and 22.4% mIoU on PASCAL Context datasets, and performs competitively to state-of-the-art transfer-learning methods requiring greater levels of supervision. We open-source our code at https://github.com/NVlabs/GroupViT .

19 February 2020 in arXiv
Verified
Preprint
Open access
PDF file
XWXiang Wang
Xiang Wang
SLSifei Liu
Sifei Liu
HMHuimin Ma
Huimin Ma
MYMing Yang
Ming Yang
Weakly-supervised semantic segmentation is a challenging task as no pixel-wise label information is provided for training. Recent methods have exploited classification networks to localize objects by selecting regions with strong response. While such response map provides sparse information, however, there exist strong pairwise relations between pixels in natural images, which can be utilized to propagate the sparse map to a much denser one. In this paper, we propose an iterative algorithm to learn such pairwise relations, which consists of two branches, a unary segmentation network which learns the label probabilities for each pixel, and a pairwise affinity network which learns affinity matrix and refines the probability map generated from the unary network. The refined results by the pairwise network are then used as supervision to train the unary network, and the procedures are conducted iteratively to obtain better segmentation progressively. To learn reliable pixel affinity without accurate annotation, we also propose to mine confident regions. We show that iteratively training this framework is equivalent to optimizing an energy function with convergence to a local minimum. Experimental results on the PASCAL VOC 2012 and COCO datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods.