Feifan Yang

Mr. Feifan Yang

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
22 July 2024 in Land
Verified
Journal Article
Open access
PDF file
JDJianshu Duan
Jianshu Duan
ZZZhao Zhengxu
Zhao Zhengxu
YXYouheng Xu
Youheng Xu
XYXiangting You
Xiangting You
FYFeifan Yang
Feifan Yang
GCGang Chen
Gang Chen
As a representative of potential “hidden champions”, a concept originating in Germany, specialized and innovative Little Giant Enterprises (LGEs) have become exemplary models for small and medium-sized enterprises (SMEs) in China. These enterprises are regarded as crucial support for realizing the strategy of building a strong manufacturing country and addressing the weaknesses in key industrial areas. This paper begins by examining urban agglomerations, which serve as the main spatial carriers for industrial restructuring and high-quality development in manufacturing. Based on data from LGEs in the Yangtze River Delta (YRD) and Pearl River Delta (PRD) urban agglomerations from 2019 to 2023, the study employs the Random Forest (RF) and Multi-scale Geographically Weighted Regression (MGWR) methods to conduct a comparative analysis of their spatial patterns and influencing factors. The results are as follows: (1) LGEs exhibit spatial clustering in both the YRD and PRD regions. Enterprises in the YRD form a “one-axis-three-core” pattern within a distance of 65 km, while enterprises in the PRD present a “single-axis” pattern within a distance of 30 km, with overall high clustering intensity. (2) The YRD is dominated by traditional manufacturing and supplemented by high-tech services. In contrast, the PRD has a balanced development of high-tech manufacturing and services. Enterprises in different industries are generally characterized by a “multi-point clustering” characteristic, of which the YRD displays a multi-patch distribution and the PRD a point–pole distribution. (3) Factors such as industrial structure, industrial platforms, and logistics levels significantly affect enterprise clustering and exhibit scale effects differences between the two urban clusters. Factors such as industrial platforms, logistics levels, and dependence on foreign trade show positive impacts, while government fiscal expenditure shows a negative impact. Natural geographical location factors exhibit opposite effects in the two regions but are not the primary determinants of enterprise distribution. Each region should leverage its own strengths, improve urban coordination and communication mechanisms within the urban cluster, strengthen the coordination and linkage of the manufacturing industry chain upstream and downstream, and promote high-tech industries, thereby enhancing economic resilience and regional competitiveness.

7 August 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
FYFeifan Yang
Feifan Yang
GCGang Chen
Gang Chen
JDJianshu Duan
Jianshu Duan
The transformer architecture is gradually gaining attention in remote sensing. Many algorithms related to this architecture have been proposed. However, the DEtection TRansformer (DETR) has been proposed as a new approach for implementing object detection tasks. It uses the transformer architecture for feature extraction, and its improved derivative models are uncommon in remote sensing object detection (RSOD). Hence, we selected the DETR with the improved deNoising anchor boxes (DINO) model as a foundation, upon which we have made improvements under the characteristics of remote sensing images (RSIs). Specifically, we proposed the skip-encoder (SE) module that can be applied to the encoder stage of the model and the skip-decoder (SD) module for the decoder stage. The SE module can enhance the model’s ability to extract multiscale features. The SD module can reduce computational complexity and maintain the model performance. The experimental results on the NWPU VHR-10 and DIOR datasets demonstrate that the SE and SD modules can improve DINO for better learning small- and medium-sized targets in RSIs. We achieved a mean average precision of 94.8% on the NWPU VHR-10 dataset and 75.6% on the DIOR dataset.

20 April 2026 in Remote Sensing
Verified
Journal Article
Open access
PDF file
DLDongjie Lian
Dongjie Lian
GCGang Chen
Gang Chen
BWBiao Wu
Biao Wu
FYFeifan Yang
Feifan Yang
Remote sensing semantic segmentation is fundamental to applications such as land-cover mapping, urban analysis, and environmental monitoring. However, remote sensing scenes often exhibit pronounced scale variation, fragmented regions, dense small objects, and complex boundary transitions, making fine-grained prediction particularly challenging. Transformer-based architectures such as SegFormer have demonstrated a strong capability in modeling long-range context through hierarchical encoding, yet their lightweight decoders mainly rely on linear projection and feature fusion, providing limited capacity for local refinement after multi-scale aggregation. This limitation may reduce spatial precision in boundary-sensitive and small-object-rich regions. To address this issue, we propose the Post-fusion Enhanced Block (PFEB), a lightweight decoder-side refinement module inserted after multi-scale feature fusion and before pixel-wise classification. PFEB combines channel expansion, depthwise and pointwise convolutions, efficient channel attention (ECA), and residual learning to enhance local semantic refinement while largely preserving computational efficiency. Built upon SegFormer, the proposed method was evaluated on two widely used remote sensing benchmarks, i.e., LoveDA and ISPRS Vaihingen, under both Mix Transformer-B0 (MiT-B0) and Mix Transformer-B2 (MiT-B2) backbones. Experimental results show that PFEB consistently improves the SegFormer baseline across datasets and model scales. Under MiT-B2 backbone, our method achieves 53.82 ± 0.31 mean intersection over union (mIoU) on LoveDA and 74.84 ± 0.41 mIoU on ISPRS Vaihingen. Boundary- and size-aware evaluations further indicate that the gains are mainly reflected in improved semantic correctness near boundaries and in the recoverability of small objects. With only modest additional cost (approximately +0.53 M parameters and +8.7 G floating point operations (FLOPs)), PFEB provides a favorable accuracy–efficiency trade-off. These results suggest that PFEB is an effective and lightweight post-fusion refinement module for improving fine-grained remote sensing semantic segmentation.