Xuelu Li

Dr. Xuelu Li


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
6 January 2022 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
XLXuelu Li
Xuelu Li
RBRaja Bala
Raja Bala
VMVishal Monga
Vishal Monga
Deep learning has enabled significant improvements in the accuracy of 3-D blood vessel segmentation. Open challenges remain in scenarios where labeled 3-D segmentation maps for training are severely limited, as is often the case in practice, and in ensuring robustness to noise. Inspired by the observation that 3-D vessel structures project onto 2-D image slices with informative and unique edge profiles, we propose a novel deep 3-D vessel segmentation network guided by edge profiles. Our network architecture comprises a shared encoder and two decoders that learn segmentation maps and edge profiles jointly. 3-D context is mined in both the segmentation and edge prediction branches by employing bidirectional convolutional long-short term memory (BCLSTM) modules. 3-D features from the two branches are concatenated to facilitate learning of the segmentation map. As a key contribution, we introduce new regularization terms that: a) capture the local homogeneity of 3-D blood vessel volumes in the presence of biomarkers; and b) ensure performance robustness to domain-specific noise by suppressing false positive responses. Experiments on benchmark datasets with ground truth labels reveal that the proposed approach outperforms state-of-the-art techniques on standard measures such as DICE overlap and mean Intersection-over-Union. The performance gains of our method are even more pronounced when training is limited. Furthermore, the computational cost of our network inference is among the lowest compared with state-of-the-art.

26 March 2020 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
XLXuelu Li
Xuelu Li
VMVishal Monga
Vishal Monga
AMAbhijit Mahalanobis
Abhijit Mahalanobis
The low resolution of infrared (IR) images makes feature extraction for classification of a challenging work. Learning-based methods, therefore, are preferred to be used on such raw imagery. In this article, in order to avoid difficulties in feature extraction, a novel multitask extension of the widely used sparse-representation-classification (SRC) method is proposed in both single and multiview set-ups. That is, the test sample could be a single IR image or images from different views. In both single-view and multiview scenarios, we try to employ collaborative spike and slab priors. This is because the traditional sparsity-inducing measures such as the l₀-row pseudonorm makes it hard to capture the sparse structure of the coefficient matrix when expanded in terms of a training dictionary, and the priors are proved to be able to capture fairly general sparse structures. Furthermore, a joint prior and sparse coefficient estimation method (JPCEM) is proposed for the first time in this article in order to alleviate the need to handpick prior parameters required before classification. Multiple experiments are conducted on a synthetic Comanche Forward Looking IR (FLIR) Automatic Target Recognition (ATR) database collected by Army Research Lab and a challenging mid-wave IR (MWIR) image ATR database made available by the U.S. Army Night Vision and Electronic Sensors Directorate. The final results substantiate the merits of the proposed JPCEM through comparisons with other state-of-the-art methods, including both the ones based on SRC and the ones constructed using deep learning frameworks.

21 May 2018 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YWYong Wang
Yong Wang
XLXuelu Li
Xuelu Li
In this paper, a novel 3-D imaging method achieved by combining the inverse synthetic aperture radar (ISAR) technique and a multiple-input-multiple-output (MIMO) radar system is presented. The high-resolution image of a target can be obtained within a limited imaging time interval, and the computational load can be reduced simultaneously because the time samples obtained by the ISAR technique can be used to play the role of space samples needed in the MIMO radar system. The adopted process of time selection method can help to realize the exact combination of the signals received by different antenna elements without producing nonequivalence between the time samples and the space samples which need to be substituted. Besides, the 2-D smoothed (2-D SL0) method, which is especially designed for 2-D signals in the compressed sensing (CS) technique, is used to realize the high-resolution imaging when there are gaps in the global observation angle without increasing the computation load or introducing the false estimated data. Furthermore, the algorithms for range alignment and velocity estimation under the 3-D imaging radar configuration are described explicitly. Finally, the simulation results are provided to prove the effectiveness of the algorithms proposed in this paper.

16 July 2019 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
XLXuelu Li
Xuelu Li
VMVishal Monga
Vishal Monga
ARArvind Rao
Arvind Rao
Objective: The diversity of tissue structure in histopathological images makes feature extraction for classification a challenging task. Dictionary learning within a sparse representation-based classification (SRC) framework has been shown to be successful for feature discovery. However, there exist stiff practical challenges: 1) computational complexity of SRC can be onerous in the decision stage since it involves solving a sparsity constrained optimization problem and often over a large number of image patches, and 2) images from distinct classes continue to share several geometric features. We propose a novel Analysis-synthesis model Learning with Shared Features algorithm (ALSF) for classifying such images more effectively. Methods: In ALSF, a joint analysis and synthesis learning model is introduced to learn the classifier and the feature extractor at the same time. Unlike SRC, no explicit optimization is needed in the inference phase leading to much reduced computation. Crucially, we introduce the learning of a low rank shared dictionary and a shared analysis operator, which more accurately represents both similarities and differences in histopathological images from distinct classes. We also develop an extension of ALSF with a sparsity constraint, whose presence or absence facilitates a cost-performance trade-off. Results: ALSF is evaluated on three challenging and well-known datasets: (1) spleen tissue images, (2) brain tumor images, and (3) Breast Cancer Tissue dataset provided by different organizations. Conclusion: Experimental results demonstrate both complexity and performance benefits of ALSF over state-of-the-art alternatives. Significance: Modeling shared features with appropriate quantitative constraints leads to significantly improved classification in histopathology.

28 August 2023 in arXiv
Verified
Preprint
Open access
PDF file
AYAmirsaeed Yazdani
Amirsaeed Yazdani
XLXuelu Li
Xuelu Li
VMVishal Monga
Vishal Monga
Active Learning (AL) for semantic segmentation is challenging due to heavy class imbalance and different ways of defining "sample" (pixels, areas, etc.), leaving the interpretation of the data distribution ambiguous. We propose "Maturity-Aware Distribution Breakdown-based Active Learning'' (MADBAL), an AL method that benefits from a hierarchical approach to define a multiview data distribution, which takes into account the different "sample" definitions jointly, hence able to select the most impactful segmentation pixels with comprehensive understanding. MADBAL also features a novel uncertainty formulation, where AL supporting modules are included to sense the features' maturity whose weighted influence continuously contributes to the uncertainty detection. In this way, MADBAL makes significant performance leaps even in the early AL stage, hence reducing the training burden significantly. It outperforms state-of-the-art methods on Cityscapes and PASCAL VOC datasets as verified in our extensive experiments.

4 April 2020 in arXiv
Verified
Preprint
Open access
PDF file
XLXuelu Li
Xuelu Li
VMVishal Monga
Vishal Monga
Fine-grained image classification has emerged as a significant challenge because objects in such images have small inter-class visual differences but with large variations in pose, lighting, and viewpoints, etc. Most existing work focuses on highly customized feature extraction via deep network architectures which have been shown to deliver state of the art performance. Given that images from distinct classes in fine-grained classification share significant features of interest, we present a new deep network architecture that explicitly models shared features and removes their effect to achieve enhanced classification results. Our modeling of shared features is based on a new group based learning wherein existing classes are divided into groups and multiple shared feature patterns are discovered (learned). We call this framework Group based deep Shared Feature Learning (GSFL) and the resulting learned network as GSFL-Net. Specifically, the proposed GSFL-Net develops a specially designed autoencoder which is constrained by a newly proposed Feature Expression Loss to decompose a set of features into their constituent shared and discriminative components. During inference, only the discriminative feature component is used to accomplish the classification task. A key benefit of our specialized autoencoder is that it is versatile and can be combined with state-of-the-art fine-grained feature extraction models and trained together with them to improve their performance directly. Experiments on benchmark datasets show that GSFL-Net can enhance classification accuracy over the state of the art with a more interpretable architecture.