Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks43 from public data
- 170
- 53
- Deep adversarial domain adaptation for breast cancer screening from mammograms43
The proposed method adopts an adversarial learning technique to perform domain adaptation using the two domains of source and target domains to improve the detection performance on the target dataset.
- 42
- 40
- 36
- Contrastive domain adaptation with consistency match for automated pneumonia diagnosis31
This work proposes a novel method called Contrastive Domain Adaptation with Consistency Match (CDACM), which outperforms several state-of-the-art unsupervised domain adaptation approaches, and verifies the effectiveness of CDACM for automated pneumonia diagnosis using chest X-ray imaging.
- 29
- 28
- A multi-stage multi-modal learning algorithm with adaptive multimodal fusion for improving multi-label skin lesion classification22
A novel uncertainty-based hybrid fusion strategy for a multi-modal learning algorithm aimed at skin cancer diagnosis that combines three different modalities: clinical images, dermoscopy images, and metadata, to make the final classification.
- 22
- 20
- 17
- A feature-wise attention module based on the difference with surrounding features for convolutional neural networks14
A feature-wise attention module is proposed, which can give each feature of the input feature map an attention weight and is based on the well-known surround suppression in the discipline of neuroscience.
- 12
- GapMatch: Bridging Instance and Model Perturbations for Enhanced Semi-Supervised Medical Image Segmentation11
A unified perturbation framework named GapMatch is proposed, which bridges instance and model perturbations to broaden the perturbation space and employs dual perturbation to impose consistency regularization on the model.
- Breast cancer X-ray image staging: based on efficient net with multi-scale fusion and cbam attention9
Compared with other existing image classification algorithms, the proposed Efficientnet model based on the cbam attention mechanism has the highest accuracy, thus the researchers conclude that EfficientNet with CBAM and multi-scale fusion will improve the classification performance.
- 9
- Performance Test of a Well-Trained Model for Meningioma Segmentation in Health Care Centers: Secondary Analysis Based on Four Retrospective Multicenter Data Sets7
Deploying the trained CNN model in different health care institutions may show significant performance degradation due to the domain shift of MRIs, and the use of unsupervised domain adaptation or supervised retraining should be considered.
- 7
- 6
- Class-Center-Based Self-Knowledge Distillation: A Simple Method to Reduce Intra-Class Variance5
This work proposes a simple improved algorithm, the center self-distillation, which achieves a better effect with almost no additional computational cost and can not only reduce intra-class variance but also greatly improve the generalization ability of modern convolutional neural networks.
- 5
- 5
- Deep Neural Network Augments Performance of Junior Residents in Diagnosing COVID-19 Pneumonia on Chest Radiographs5
While the AI model improved junior residents’ performance, a decline in performance was observed on the external test compared to the internal test set, suggesting a domain shift between the patient dataset and the external dataset, highlighting the need for future research on test-time training domain adaptation to address this issue.
- 4
- 4
- Rethinking Out-of-Distribution Detection and Generalization with Collective Behavior Dynamics2
This paper proposes that the potential is well-characterized by a Fourier-domain form of the Poisson equation, and rivals the SoTA approaches for OOD generalization and can be seamlessly integrated with them to deliver additional gains.
- Discussion on the Feasibility of Soft Actuator as an Assistive Tool for Seniors in Minimally Invasive Surgery2
This work presents a new elastomeric pneumatic actuator with air chambers for the purpose of MIS support, and showed that the proposed actuator achieved a 180° bending angle readily, with a small sweeping area when going through a narrow cavity.
- DualFete: Revisiting Teacher-Student Interactions from a Feedback Perspective for Semi-supervised Medical Image Segmentation1
This work introduces a feedback mechanism into the teacher-student framework to counteract error reconfirmations, and proposes a dual-teacher feedback model, which allows more dynamics in the feedback loop and fosters more gains by resolving disagreements through cross-teacher supervision while avoiding consistent errors.
- GAPNet: A Lightweight Framework for Image and Video Salient Object Detection via Granularity-aware Paradigm1
GAPNet is presented, a lightweight network built on the granularity-aware paradigm for both image and video SOD models that achieves a new state-of-the-art performance among lightweight image and video SOD models.
- 1
- Physics-Driven 3D Gaussian Rendering for Zero-Shot MRI Super-Resolution1
A zero-shot MRI SR framework using explicit Gaussian representation to balance data requirements and efficiency is proposed, and a brick-based order-independent rasterization scheme enables highly parallel 3D computation, lowering training and inference costs.
- Local Extremum Mapping for Weak Supervision Learning on Mammogram Classification and Localization1
A novel local extremum mapping mechanism is proposed for mammogram classification and weakly supervised lesion localization that effectively localizes lesions with a dice similarity coefficient of 0.37, outperforming Grad-CAM and other baseline approaches.
- 1
- 1
- 1
- –
- V2-Former: Towards volumetric framework for instance-level segmentation and prediction of fetal ventriculomegaly in anisotropic MRI–
V2-Former is introduced, a Volumetric Ventricular analysis framework that achieves both ventricle-specific prediction consistent with clinical practice and comprehensive volumetric assessment, and the first end-to-end solution that delivers both ventricle-specific predictions and volumetric evaluations to support clinical VM assessment.
- Structured Semantic Cloaking for Jailbreak Attacks on Large Language Models–
Structured Semantic Cloaking (S2C), a novel multi-dimensional jailbreak attack framework that manipulates how malicious semantic intent is reconstructed during model inference, is proposed and evaluated across multiple open-source and proprietary LLMs.
- –
- –
- Study of colony image segmentation algorithm based on wavelet transform and watershed transform–
Experiments results show that the colony images can be well segmented by the new algorithm.
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar; position from the scholar’s ORCID record, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.