Zhihang Fu

Zhihang Fu

Auto-generated profile, based on publicly available information

Zhihang Fu

Alibaba Cloud, Hangzhou, China

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
25 November 2024 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
KLKai Liu
Kai Liu
ZFZhihang Fu
Zhihang Fu
SJSheng Jin
Sheng Jin
ZCZe Chen
Ze Chen
FZFan Zhou
Fan Zhou
JYJieping Ye
Jieping Ye
Enlarging input images is a straightforward and effective approach to promote small object detection. However, simple image enlargement is significantly expensive on both computations and GPU memory. In fact, small objects are usually sparsely distributed and locally clustered. Therefore, massive feature extraction computations are wasted on the non-target background area of images. Recent works have tried to pick out target-containing regions using an extra network and perform conventional object detection, but the newly introduced computation limits their final performance. In this paper, we propose to reuse the detector’s backbone to conduct feature-level object-seeking and patch-slicing, which can avoid redundant feature extraction and reduce the computation cost. Incorporating with a sparse detection head, we are able to detect small objects on high-resolution inputs (e.g., 1080P or larger) for superior performance. The resulting Efficient Small Object Detection (ESOD) approach is a generic framework, which can be applied to both CNN- and ViT-based detectors to save the computation and GPU memory costs. Extensive experiments demonstrate the efficacy and efficiency of our method. In particular, our method consistently surpasses the SOTA detectors by a large margin (e.g., 8% gains on AP) on the representative VisDrone, UAVDT, and TinyPerson datasets. Code will be made public soon.

1 December 2021 in Image and Vision Computing
Verified
Journal Article
Closed access
ZCZe Chen
Ze Chen
ZFZhihang Fu
Zhihang Fu
JHJianqiang Huang
Jianqiang Huang
MTMingyuan Tao
Mingyuan Tao
RJRongxin Jiang
Rongxin Jiang
XHXian-Sheng Hua
Xian-Sheng Hua

25 February 2019 in IEEE Access
Verified
Journal Article
Open access
ZFZhihang Fu
Zhihang Fu
YCYaowu Chen
Yaowu Chen
RJRongxin Jiang
Rongxin Jiang
Pedestrian detection attracts much attention from the academic community since it is an essential and significant component of autonomous driving. Despite many similarities with general object detection, pedestrian detection still has unique challenges such as background false positives and missed detections in a crowd. In this paper, we explore the value of contextual information for pedestrian detection, arguing that contextual information is not a panacea in all cases. Despite the importance of enriching context, a method should focus on the core area where there is the target instance. To this end, we propose a pedestrian detection framework that extends proposals to enrich the context and relieves the confusions caused by contextual information through a supervised attention module. The ablation study demonstrates that the proposal extension is effective for both crowded and non-crowded instances, moreover the attention module narrows the precision gap between these two cases. Extensive experiments on commonly used pedestrian benchmarks are conducted, which show the superior performance of our method.We achieve the average precision of 74.78% on KITTI pedestrian benchmark with the hard metric level, ranking the first places among all methods.