Fu-En Wang

Fu-En Wang

Auto-generated profile, based on publicly available information

Fu-En Wang

National Tsing Hua University

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
1 September 2022 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
FWFu-En Wang
Fu-En Wang
YYYu-Hsuan Yeh
Yu-Hsuan Yeh
YTYi-Hsuan Tsai
Yi-Hsuan Tsai
WCWei-Chen Chiu
Wei-Chen Chiu
MSMin Sun
Min Sun
Due to the rise of spherical cameras, monocular 360 $^\circ$ depth estimation becomes an important technique for many applications (e.g., autonomous systems). Thus, state-of-the-art frameworks for monocular 360 $^\circ$ depth estimation such as bi-projection fusion in BiFuse are proposed. To train such a framework, a large number of panoramas along with the corresponding depth ground truths captured by laser sensors are required, which highly increases the cost of data collection. Moreover, since such a data collection procedure is time-consuming, the scalability of extending these methods to different scenes becomes a challenge. To this end, self-training a network for monocular depth estimation from 360 $^\circ$ videos is one way to alleviate this issue. However, there are no existing frameworks that incorporate bi-projection fusion into the self-training scheme, which highly limits the self-supervised performance since bi-projection fusion can leverage information from different projection types. In this paper, we propose BiFuse++ to explore the combination of bi-projection fusion and the self-training scenario. To be specific, we propose a new fusion module and Contrast-Aware Photometric Loss to improve the performance of BiFuse and increase the stability of self-training on real-world videos. We conduct both supervised and self-supervised experiments on benchmark datasets and achieve state-of-the-art performance.

26 May 2019
Verified
Book Chapter
Closed access
PDF file
FWFu-En Wang
Fu-En Wang
HHHou-Ning Hu
Hou-Ning Hu
HCHsien-Tzu Cheng
Hsien-Tzu Cheng
JLJuan-Ting Lin
Juan-Ting Lin
SYShang-Ta Yang
Shang-Ta Yang
MSMin Sun
Min Sun

26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
FWFu-En Wang
Fu-En Wang
CWChien-Yi Wang
Chien-Yi Wang
MSMin Sun
Min Sun
SLShang-Hong Lai
Shang-Hong Lai
Although significant progress has been made in face recognition, demographic bias still exists in face recognition systems. For instance, it usually happens that the face recognition performance for a certain demographic group is lower than the others. In this paper, we propose MixFairFace framework to improve the fairness in face recognition models. First of all, we argue that the commonly used attribute-based fairness metric is not appropriate for face recognition. A face recognition system can only be considered fair while every person has a close performance. Hence, we propose a new evaluation protocol to fairly evaluate the fairness performance of different approaches. Different from previous approaches that require sensitive attribute labels such as race and gender for reducing the demographic bias, we aim at addressing the identity bias in face representation, i.e., the performance inconsistency between different identities, without the need for sensitive attribute labels. To this end, we propose MixFair Adapter to determine and reduce the identity bias of training samples. Our extensive experiments demonstrate that our MixFairFace approach achieves state-of-the-art fairness performance on all benchmark datasets.

11 April 2019 in arXiv
Verified
Preprint
Open access
PDF file
TWTsun-Hsuan Wang
Tsun-Hsuan Wang
FWFu-En Wang
Fu-En Wang
JLJuan-Ting Lin
Juan-Ting Lin
YTYi-Hsuan Tsai
Yi-Hsuan Tsai
WCWei-Chen Chiu
Wei-Chen Chiu
MSMin Sun
Min Sun
We propose a novel plug-and-play (PnP) module for improving depth prediction with taking arbitrary patterns of sparse depths as input. Given any pre-trained depth prediction model, our PnP module updates the intermediate feature map such that the model outputs new depths consistent with the given sparse depths. Our method requires no additional training and can be applied to practical applications such as leveraging both RGB and sparse LiDAR points to robustly estimate dense depth map. Our approach achieves consistent improvements on various state-of-the-art methods on indoor (i.e., NYU-v2) and outdoor (i.e., KITTI) datasets. Various types of LiDARs are also synthesized in our experiments to verify the general applicability of our PnP module in practice. For project page, see https://zswang666.github.io/PnP-Depth-Project-Page/

18 September 2023 in arXiv
Verified
Preprint
Open access
PDF file
TLTing-Ying Lin
Ting-Ying Lin
LHLin-Yung Hsieh
Lin-Yung Hsieh
FWFu-En Wang
Fu-En Wang
WWWen-Shen Wuen
Wen-Shen Wuen
MSMin Sun
Min Sun
We propose a sparse and privacy-enhanced representation for Human Pose Estimation (HPE). Given a perspective camera, we use a proprietary motion vector sensor(MVS) to extract an edge image and a two-directional motion vector image at each time frame. Both edge and motion vector images are sparse and contain much less information (i.e., enhancing human privacy). We advocate that edge information is essential for HPE, and motion vectors complement edge information during fast movements. We propose a fusion network leveraging recent advances in sparse convolution used typically for 3D voxels to efficiently process our proposed sparse representation, which achieves about 13x speed-up and 96% reduction in FLOPs. We collect an in-house edge and motion vector dataset with 16 types of actions by 40 users using the proprietary MVS. Our method outperforms individual modalities using only edge or motion vector images. Finally, we validate the privacy-enhanced quality of our sparse representation through face recognition on CelebA (a large face dataset) and a user study on our in-house dataset.

30 March 2020 in arXiv
Verified
Preprint
Open access
PDF file
FWFu-En Wang
Fu-En Wang
YYYu-Hsuan Yeh
Yu-Hsuan Yeh
MSMin Sun
Min Sun
WCWei-Chen Chiu
Wei-Chen Chiu
YTYi-Hsuan Tsai
Yi-Hsuan Tsai
Inferring the information of 3D layout from a single equirectangular panorama is crucial for numerous applications of virtual reality or robotics (e.g., scene understanding and navigation). To achieve this, several datasets are collected for the task of 360 layout estimation. To facilitate the learning algorithms for autonomous systems in indoor scenarios, we consider the Matterport3D dataset with their originally provided depth map ground truths and further release our annotations for layout ground truths from a subset of Matterport3D. As Matterport3D contains accurate depth ground truths from time-of-flight (ToF) sensors, our dataset provides both the layout and depth information, which enables the opportunity to explore the environment by integrating both cues.