YSYuhang Sun

Yuhang Sun

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yuhang Sun has a total of 6 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Salient Object Detection in Traffic Scene Through the TSOD10K Dataset

    by Yu Qiu, Yuhang Sun, Jie Mei, Lin Xiao, Jing Xu

    Traffic Salient Object Detection (TSOD) aims to segment the objects critical to driving safety by combining semantic (e.g., collision risks) and visual saliency. Unlike SOD in natural scene images (NSI-SOD), which prioritizes visually distinctive regions, TSOD emphasizes the objects that demand immediate driver attention due to their semantic impact, even with low visual contrast. This dual criterion, i.e., bridging perception and contextual risk, re-defines saliency for autonomous and assisted driving systems. To address the lack of task-specific benchmarks, we collect the first large-scale TSOD dataset with pixel-wise saliency annotations, named TSOD10K. TSOD10K covers the diverse object categories in various real-world traffic scenes under various challenging weather/illumination variations (e.g., fog, snowstorms, low-contrast, and low-light). Methodologically, we propose a Mamba-based TSOD model, termed Tramba. Considering the challenge of distinguishing inconspicuous visual information from complex traffic backgrounds, Tramba introduces a novel Dual-Frequency Visual State Space module equipped with shifted window partitioning and dilated scanning to enhance the perception of fine details and global structure by hierarchically decomposing high/low-frequency components. To emphasize critical regions in traffic scenes, we propose a traffic-oriented Helix 2D-Selective-Scan (Helix-SS2D) mechanism that injects driving attention priors while effectively capturing global multi-direction spatial dependencies. We establish a comprehensive benchmark by evaluating Tramba and 25 existing NSI-SOD models on TSOD10K, demonstrating Tramba’s superiority. Our research establishes the first foundation for safety-aware saliency analysis in intelligent transportation systems. The dataset and code will be made publicly available at https://github.com/mj129/Tramba.


  • Deeply Hybrid Contrastive Learning Based on Semantic Pseudo-Label for Salient Object Detection in Optical Remote Sensing Images

    by Yu Qiu, Yuhang Sun, Jie Mei, Jing Xu

    Salient object detection in natural scene images (NSI-SOD) has undergone remarkable advancements in recent years. However, compared to those of natural images, the properties of remote sensing images (ORSIs), such as diverse spatial resolutions, complex background structures, and varying visual attributes of objects, are more complicated. Hence, how to explore the multiscale structural perceptual information of ORSIs to accurately detect salient objects is more challenging. In this paper, inspired by the superiority of contrastive learning, we propose a novel training paradigm for ORSI-SOD, named Deeply Hybrid Contrastive Learning Based on Semantic Pseudo-Label (DHCont), to force the network to extract rich structural perceptual information and further learn the better-structured feature embedding spaces. Specifically, DHCont first splits the ORSI into several local subregions composed of color- and texture-similar pixels, which act as semantic pseudo-labels. This strategy can effectively explore the underdeveloped semantic categories in ORSI-SOD. To delve deeper into multiscale structure-aware optimization, DHCont incorporates a hybrid contrast strategy that integrates “pixel-to-pixel”, “region-to-region”, “pixel-to-region”, and “region-to-pixel” contrasts at multiple scales. Additionally, to enhance the edge details of salient regions, we develop a hard edge contrast strategy that focuses on improving the detection accuracy of hard pixels near the object boundary. Moreover, we introduce a deep contrast algorithm that adds additional deep-level constraints to the feature spaces of multiple stages. Extensive experiments on two popular ORSI-SOD datasets demonstrate that simply integrating our DHCont into the existing ORSI-SOD models can significantly improve the performance.


  • Lightweight Cross-Modal Information Measure and Propagation for Road Extraction From Remote Sensing Image and Trajectory/LiDAR

    by Yu Qiu, Chenyu Lin, Jie Mei, Yuhang Sun, Haotian Lu, Jing Xu

    Recent studies have confirmed that GPS trajectory can effectively assist in achieving more accurate road extraction from remote sensing images. Therefore, lots of efforts focus on designing effective multi-modal fusion strategies for GPS trajectory and remote sensing image modalities. However, there are still some limitations, e.g ., the fusion structures are complex and hinder further improvements. Moreover, the negative impact of redundant information in various modalities is commonly ignored. This paper aims to design a simple yet effective fusion strategy for GPS trajectory and remote sensing image modalities to address the above issues. Inspired by the network pruning algorithm, we design a Cross-Modal Information Propagation (CMIP) mechanism. CMIP utilizes the scaling factors and sparse constraint to distinguish the redundant information of a certain modality that is directly replaced with corresponding information of another modality. We improve the widely-used L1 sparse constraint and propose a novel information balanced constraint which is added on the scaling factors to better identify and prune redundant channels. Embedded in the CMIP mechanism, a multi-modal information propagation network (CMIPNet) is proposed, which can fully explore the complementarities between different modalities to accurately locate roads, especially roads with noise or incomplete information of a certain modality. Since the CMIP is parameter-free and self-adaptive, CMIPNet is lightweight and easy to deploy. The parameter number of CMIPNet can be comparable to single-modal models, which is about 1/3 of the existing multi-modal models. Extensive experiments are performed to demonstrate that CMIPNet outperforms the previous single- and multi-modal road extraction methods.