Automatic Static Vulnerability Detection for Machine Learning Libraries: Are We There Yet?

NS Harzevili, J Shin, J Wang, S Wang… - 2023 IEEE 34th …, 2023 - ieeexplore.ieee.org
Automatic detection of software security vulnerabilities is critical in software quality
assurance. Many static analysis tools that can help detect security vulnerabilities have been …

Encoder deep interleaved network with multi-scale aggregation for RGB-D salient object detection

G Feng, J Meng, L Zhang, H Lu - Pattern Recognition, 2022 - Elsevier
Recently, RGB-D salient object detection (SOD) has aroused widespread research interest.
Existing RGB-D SOD approaches mainly consider the cross-modal information fusion in the …

H-ProMed: Ultrasound image segmentation based on the evolutionary neural network and an improved principal curve

T Peng, J Zhao, Y Gu, C Wang, Y Wu, X Cheng, J Cai - Pattern Recognition, 2022 - Elsevier
The purpose of this work is to develop a method for accurate and robust prostate
segmentation in transrectal ultrasound (TRUS) images. These images are difficult to …

Answering knowledge-based visual questions via the exploration of question purpose

L Song, J Li, J Liu, Y Yang, X Shang, M Sun - Pattern Recognition, 2023 - Elsevier
Visual question answering has been greatly advanced by deep learning technologies, but
still remains an open problem subjected to two aspects of factors. First, previous works …

Automatic static bug detection for machine learning libraries: Are we there yet?

J Shin, J Wang, S Wang, N Nagappan - arxiv preprint arxiv:2307.04080, 2023 - arxiv.org
Automatic detection of software bugs is a critical task in software security. Many static tools
that can help detect bugs have been proposed. While these static bug detectors are mainly …

Progressive expansion for semi-supervised bi-modal salient object detection

J Wang, Z Zhang, N Yu, Y Han - Pattern Recognition, 2025 - Elsevier
Existing bi-modal salient object detection (SOD) methods primarily rely on fully supervised
training strategies that require extensive manual annotation. Undoubtedly, extensive manual …

Test time adaptation with regularized loss for weakly supervised salient object detection

O Veksler - Proceedings of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
It is well known that CNNs tend to overfit to the training data. Test-time adaptation is an
extreme approach to deal with overfitting: given a test image, the aim is to adapt the trained …

Characterizing and understanding software security vulnerabilities in machine learning libraries

NS Harzevili, J Shin, J Wang, S Wang… - 2023 IEEE/ACM 20th …, 2023 - ieeexplore.ieee.org
The application of machine learning (ML) libraries has tremendously increased in many
domains, including autonomous driving systems, medical, and critical industries …

BALQUE: Batch active learning by querying unstable examples with calibrated confidence

Y Han, D Liu, J Shang, L Zheng, J Zhong, W Cao… - Pattern Recognition, 2024 - Elsevier
Active learning alleviates labeling costs by selecting and labeling the most informative
examples from an unlabeled pool. However, most existing active learning approaches …

Active deep learning from a noisy teacher for semi-supervised 3D image segmentation: Application to COVID-19 pneumonia infection in CT

MA Hussain, Z Mirikharaji, M Momeny… - … Medical Imaging and …, 2022 - Elsevier
Supervised deep learning has become a standard approach to solving medical image
segmentation tasks. However, serious difficulties in attaining pixel-level annotations for …