Hong Zhang

Hong Zhang

Auto-generated profile, based on publicly available information

Hong Zhang

School of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
11 February 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
HZHong Zhang
Hong Zhang
YTYuhang Teng
Yuhang Teng
HLHaojie Li
Haojie Li
ZWZhihui Wang
Zhihui Wang
Vision transformers have achieved impressive performance in addressing spatial-temporal inconsistencies of change detection due to their ability to model long-range dependencies in bitemporal features. However, applying the self-attention operation directly to bitemporal features causes feature confusion and incurs high computational complexity. In this paper, we propose a novel change detection framework based on Spatial-Temporal Robust representation (STRobustNet). To avoid directly applying self-attention to bitemporal features, we derive a collection of spatial-temporal robust representations for land-use classes of interest. These representations are used to transform spatial-temporally inconsistent bitemporal features into consistent bitemporal classification representations, enhancing model efficiency and reducing feature confusion. Specifically, to fully perceive and integrate the varied appearances of the same class while minimizing deviation from the current input samples, we design a Robust Representations Generation Module, which utilizes the universal spatial-temporal context provided by the entire dataset and the specific spatial-temporal context from the current bitemporal images to generate robust representations for the interested land-use classes, improving robustness to spatial-temporal inconsistencies. Then these representations are used to activate bitemporal features in different class channels, producing spatial-temporally consistent classification representations. Change detection is ultimately performed using these consistent representations, effectively avoiding false detections caused by spatial-temporal inconsistencies. Experimental results demonstrate that STRobustNet achieves performance comparable to top-performing methods, and offers the fastest inference speed among transformer-based methods. Code and pretrained models are available at https://github.com/DLUTTengYH/STRobustNet.

6 December 2021 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
HZHong Zhang
Hong Zhang
XYXinchen Ye
Xinchen Ye
SCShenglun Chen
Shenglun Chen
ZWZhihui Wang
Zhihui Wang
HLHaojie Li
Haojie Li
WOWanli Ouyang
Wanli Ouyang
Existing stereo matching methods achieve satisfactory average accuracy on a whole predicted disparity map under common global metrics, but ignore the fine-grained performance at region level, especially for far regions in the scene, which is more crucial in actual auto-driving scenarios. There are two factors accounting for this problem: 1) Depth resolution. Existing methods use disparity-based sampling to extract matching candidates uniformly according to the disparity range, but leads to sparser sampling density at far regions than that of close regions in terms of depth range, resulting in low depth resolution in far regions. 2) Feature discriminability. Limited image resolution and inferior feature extraction at far regions result in the obtained features with low discrimination, which influences the subsequent matching process between stereo images. To improve the estimation accuracy of far regions and thus achieve a balanced performance at region level, we design a novel two-stage Balanced Stereo Matching Network (BSMNet) to address the above problems. The coarse stage of BSMNet introduces a direct depth-based sampling strategy, which generates matching candidates according to scene depth instead of disparity, thus improving the depth resolution and obtaining initial depth map with more balanced accuracy. Then, a depth refinement stage is proposed to solve the problem of low feature discriminability and further optimizes the initial depth map obtained from the coarse stage. It selects matching candidates and computes their similarity scores from a carefully designed adaptive feature volume guided by a learnable scale map, thus making the final estimation more accurate. Different from the existing methods that construct stereo matching based on disparity prediction, our proposed pipeline is to directly optimize on depth information. Experiments show that our BSMNet can obtain an obvious performance improvement at far regions without discarding that at close regions, so as to largely outperform existing state-of-the-art methods.

15 February 2024 in Information Fusion
Verified
Journal Article
Closed access
HZHong Zhang
Hong Zhang
YYYuxin Yue
Yuxin Yue
HLHaojie Li
Haojie Li
PLPan Liu
Pan Liu
YJYusheng Jia
Yusheng Jia
ZWZhihui Wang
Zhihui Wang

1 January 2025 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
SCShenglun Chen
Shenglun Chen
XMXinzhu Ma
Xinzhu Ma
HZHong Zhang
Hong Zhang
HLHaojie Li
Haojie Li
ZWZhihui Wang
Zhihui Wang
Depth completion is a pivotal challenge in computer vision, aiming at reconstructing the dense depth map from a sparse one, typically with a paired RGB image. Existing learning-based models rely on carefully prepared but limited data, leading to significant performance degradation in out-of-distribution (OOD) scenarios. Recent foundation models have demonstrated exceptional robustness in monocular depth estimation through large-scale training, and using such models to enhance the robustness of depth completion models is a promising solution. In this work, we propose a novel depth completion framework that leverages depth foundation models to attain remarkable robustness without large-scale training. Specifically, we leverage a depth foundation model to extract environmental cues, including structural and semantic context, from RGB images to guide the propagation of sparse depth information into missing regions. We further design a dual-space propagation approach, without any learnable parameters, to effectively propagates sparse depth in both 3D and 2D spaces to maintain geometric structure and local consistency. To refine the intricate structure, we introduce a learnable correction module to progressively adjust the depth prediction towards the real depth. We train our model on the NYUv2 and KITTI datasets as in-distribution datasets and extensively evaluate the framework on 16 other datasets. Our framework performs remarkably well in the OOD scenarios and outperforms existing state-of-the-art depth completion methods. Our models are released in this link.

28 September 2024 in Pattern Recognition
Verified
Journal Article
Closed access
NWNing Wang
Ning Wang
WWWei Wang
Wei Wang
HYHairui Yang
Hairui Yang
HZHong Zhang
Hong Zhang
ZWZhiyong Wang
Zhiyong Wang
HLHaojie Li
Haojie Li

19 October 2026 in Expert Systems with Applications
Verified
Journal Article
Closed access
KGKe Guo
Ke Guo
YZYuli Zhang
Yuli Zhang
HZHong Zhang
Hong Zhang
HLHaojie Li
Haojie Li