Yuyu Jia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yuyu Jia has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Fangyuan Xie
Northwestern Polytechnical University
1 shared publication - Huimin Chen
Northwestern Polytechnical University
1 shared publication - Junyu Gao
Northwestern Polytechnical University, Xi'an, China
1 shared publication - Qi Wang
Northwestern Polytechnical University, Xi'an, China
1 shared publication - Qiang Li
School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xian, China
1 shared publication - Rong Wang
Northwestern Polytechnical University
1 shared publication
Latest Publications
- 17 October 2025
- Published by Springer Nature
- p. 69-83
High-Order Anchor Graph-Based Clustering for Efficient Structured Proximity Matrix Learning
- 17 October 2025
- Published by Springer Nature
- p. 69-83
High-Order Anchor Graph-Based Clustering for Efficient Structured Proximity Matrix Learning
- Open Access
Embedding Generalized Semantic Knowledge into Few-Shot Remote Sensing Segmentation
Few-shot segmentation (FSS) for remote sensing (RS) imagery leverages supporting information from limited annotated samples to achieve query segmentation of novel classes. Previous efforts are dedicated to mining segmentation-guiding visual cues from a constrained set of support samples. However, they still struggle to address the pronounced intra-class differences in RS images, as sparse visual cues make it challenging to establish robust class-specific representations. In this paper, we propose a holistic semantic embedding (HSE) approach that effectively harnesses general semantic knowledge, i.e., class description (CD) embeddings.Instead of the naive combination of CD embeddings and visual features for segmentation decoding, we investigate embedding the general semantic knowledge during the feature extraction stage.Specifically, in HSE, a spatial dense interaction module allows the interaction of visual support features with CD embeddings along the spatial dimension via self-attention.Furthermore, a global content modulation module efficiently augments the global information of the target category in both support and query features, thanks to the transformative fusion of visual features and CD embeddings.These two components holistically synergize general CD embeddings and visual cues, constructing a robust class-specific representation.Through extensive experiments on the standard FSS benchmark, the proposed HSE approach demonstrates superior performance compared to peer work, setting a new state-of-the-art.
Open AccessEmbedding Generalized Semantic Knowledge into Few-Shot Remote Sensing Segmentation
Few-shot segmentation (FSS) for remote sensing (RS) imagery leverages supporting information from limited annotated samples to achieve query segmentation of novel classes. Previous efforts are dedicated to mining segmentation-guiding visual cues from a constrained set of support samples. However, they still struggle to address the pronounced intra-class differences in RS images, as sparse visual cues make it challenging to establish robust class-specific representations. In this paper, we propose a holistic semantic embedding (HSE) approach that effectively harnesses general semantic knowledge, i.e., class description (CD) embeddings.Instead of the naive combination of CD embeddings and visual features for segmentation decoding, we investigate embedding the general semantic knowledge during the feature extraction stage.Specifically, in HSE, a spatial dense interaction module allows the interaction of visual support features with CD embeddings along the spatial dimension via self-attention.Furthermore, a global content modulation module efficiently augments the global information of the target category in both support and query features, thanks to the transformative fusion of visual features and CD embeddings.These two components holistically synergize general CD embeddings and visual cues, constructing a robust class-specific representation.Through extensive experiments on the standard FSS benchmark, the proposed HSE approach demonstrates superior performance compared to peer work, setting a new state-of-the-art.