Xin Lu

Xin Lu

Auto-generated profile, based on publicly available information

Xin Lu

School of Automation, Southeast University, Nanjing, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
26 October 2023
Verified
Conference Paper
Open access
XLXin Lu
Xin Lu
SCShikun Chen
Shikun Chen
YCYichao Cao
Yichao Cao
XZXin Zhou
Xin Zhou
XLXiaobo Lu
Xiaobo Lu
In recent years, hashing methods have been popular in the large-scale media search for low storage and strong representation capabilities. To describe objects with similar overall appearance but subtle differences, more and more studies focus on hashing-based fine-grained image retrieval. Existing hashing networks usually generate both local and global features through attention guidance on the same deep activation tensor, which limits the diversity of feature representations. To handle this limitation, we substitute convolutional descriptors for attention-guided features and propose an Attributes Grouping and Mining Hashing (AGMH), which groups and embeds the category-specific visual attributes in multiple descriptors to generate a comprehensive feature representation for efficient fine-grained image retrieval. Specifically, an Attention Dispersion Loss (ADL) is designed to force the descriptors to attend to various local regions and capture diverse subtle details. Moreover, we propose a Stepwise Interactive External Attention (SIEA) to mine critical attributes in each descriptor and construct correlations between fine-grained attributes and objects. The attention mechanism is dedicated to learning discrete attributes, which will not cost additional computations in hash codes generation. Finally, the compact binary codes are learned by preserving pairwise similarities. Experimental results demonstrate that AGMH consistently yields the best performance against state-of-the-art methods on fine-grained benchmark datasets.

4 January 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
XLXin Lu
Xin Lu
YCYichao Cao
Yichao Cao
SCShikun Chen
Shikun Chen
WLWeixuan Li
Weixuan Li
XZXin Zhou
Xin Zhou
XLXiaobo Lu
Xiaobo Lu

21 March 2026 in Pattern Recognition
Verified
Journal Article
Closed access
SJShukun Jia
Shukun Jia
SHShiyu Hu
Shiyu Hu
YCYichao Cao
Yichao Cao
FYFeng Yang
Feng Yang
XLXin Lu
Xin Lu
XLXiaobo Lu
Xiaobo Lu

11 November 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
XLXin Lu
Xin Lu
YPYixuan Pan
Yixuan Pan
YCYichao Cao
Yichao Cao
XZXin Zhou
Xin Zhou
XLXiaobo Lu
Xiaobo Lu
In few-shot fine-grained recognition (FS-FGR) tasks, the main challenge is to distinguish novel categories with high intra-class variations and low inter-class differences given scarce training data. Existing studies explore discriminative features through a compact network to avoid overfitting, while they achieve marginal performance gain owing to the limited representation capability. Motivated by the significant progress of the vision foundation model, we introduce it to describe visual attributes and boost the performance of the compact feature extractor. A few-shot fine-grained recognition method with Variational Feature Imitation Conditioned on Visual Descriptions, VFI-CVD for short, has been proposed in this paper. It simultaneously exploits the pre-trained knowledge from a vision foundation model and the expert knowledge mined by a feature extractor. Specifically, the intra-class variations shared across object categories are encoded into a common distribution thus we can augment features by sampling latent variables. To enhance the learning of intra-class variations, a condition exchange strategy (CES) is put forward to interact the knowledge between samples through feature cross-imitation. In the inference stage, the learned knowledge is further integrated through the joint prediction of visual descriptions and cross-imitated features. Comprehensive experimental results on four fine-grained benchmark datasets show that the proposed VFI-CVD achieves state-of-the-art performance, e.g., 90.37% under the 5-way 1-shot setting on CUB-200-2011. It surpasses existing methods by a large margin, especially in the challenging 30-way recognition tasks and cross-domain evaluation. The source code is publicly available: https://github.com/Lx-zjwf/VFI-CVD.

6 June 2023 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
XLXin Lu
Xin Lu
WLWeixuan Li
Weixuan Li
XLXiaobo Lu
Xiaobo Lu

12 November 2025 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
SCShikun Chen
Shikun Chen
XLXin Lu
Xin Lu
XLXiaobo Lu
Xiaobo Lu