Face forgery detection aims to distinguish AI generated fake faces with real faces. With the rapid development of face forgery creation algorithms, a large number of generative models have been proposed, which gradually reduce the local distortion phenomenon or the specific frequency traces in these models. At the same time, in the process of face data compression and transmission, distortion phenomenon and specific frequency cues could be eliminated, which brings severe challenges to the performance and generalization ability of face forgery detection.
View Article and Find Full Text PDFPurpose: This study investigated the proteomic landscape of exfoliation glaucoma to find potential biomarkers.
Methods: The study enrolled 34 patients diagnosed with either exfoliation syndrome with/without glaucoma or age-related cataract. Plasma proteins were analyzed through mass spectrometry and Mendelian randomization (MR) based on data from deCODE, FinnGen, Atherosclerosis Risk in Communities (ARIC), eQTLGen, and UK Biobank (UKB) cohorts to infer relationships.
Multi-modal image synthesis is crucial for obtaining complete modalities due to the imaging restrictions in reality. Current methods, primarily CNN-based models, find it challenging to extract global representations because of local inductive bias, leading to synthetic structure deformation or color distortion. Despite the significant global representation ability of transformer in capturing long-range dependencies, its huge parameter size requires considerable training data.
View Article and Find Full Text PDFIEEE Trans Pattern Anal Mach Intell
February 2025
Adversarial training has been proposed and widely recognized as a very effective method to defend against adversarial noise. However, the label flipping pattern on different classes still need deeper exploration to identify potential problems and assist in further enhancing robustness. In this work, we model the class-flipping distribution via statistical investigations and find this distribution reveals two shortcomings: the highly misleading category is present in the model's predictions for data in each class, and the trend in class flipping are significantly different across classes.
View Article and Find Full Text PDFIEEE Trans Neural Netw Learn Syst
January 2025
Compositional zero-shot learning (CZSL) aims to identify unobservable compositional concepts with prior knowledge of known primitives (attributes and objects). Due to distribution differences between seen and unseen components, existing methods for CZSL often ignore intrinsic variations between primitives and suffer from domain bias problems. To address this challenge, we proposed a concept-aware graph convolutional network (GCN) that utilizes cross-attentions to extract features unique to attributes and objects from paired concept-sharing inputs.
View Article and Find Full Text PDFIEEE Trans Image Process
January 2025
Semi-Supervised Object Detection (SSOD) aims to improve the utilization of unlabeled data, and various methods, such as adaptive threshold techniques, have been extensively studied to increase exploitable information. However, these methods are passive, relying solely on the original image data. Additionally, existing approaches prioritize the predicted categories of the teacher model while overlooking the relationships between different categories in the prediction.
View Article and Find Full Text PDFIEEE Trans Med Imaging
January 2025
Existing studies of multi-modality medical image segmentation tend to aggregate all modalities without discrimination and employ multiple symmetric encoders or decoders for feature extraction and fusion. They often overlook the different contributions to visual representation and intelligent decisions among multi-modality images. Motivated by this discovery, this paper proposes an asymmetric adaptive heterogeneous network for multi-modality image feature extraction with modality discrimination and adaptive fusion.
View Article and Find Full Text PDFExisting free-energy guided No-Reference Image Quality Assessment (NR-IQA) methods continue to face challenges in effectively restoring complexly distorted images. The features guiding the main network for quality assessment lack interpretability, and efficiently leveraging high-level feature information remains a significant challenge. As a novel class of state-of-the-art (SOTA) generative model, the diffusion model exhibits the capability to model intricate relationships, enhancing image restoration effectiveness.
View Article and Find Full Text PDFIEEE Trans Neural Netw Learn Syst
January 2025
Traditional clustering algorithms often focus on the most fine-grained information and achieve clustering by calculating the distance between each pair of data points or implementing other calculations based on points. This way is not inconsistent with the cognitive mechanism of "global precedence" in the human brain, resulting in those methodsbad performance in efficiency, generalization ability, and robustness. To address this problem, we propose a new clustering algorithm called granular-ball clustering via granular-ball computing.
View Article and Find Full Text PDFAlthough numerous clustering algorithms have been developed, many existing methods still rely on the K-means technique to identify clusters of data points. However, the performance of K-means is highly dependent on the accurate estimation of cluster centers, which is challenging to achieve optimally. Furthermore, it struggles to handle linearly non-separable data.
View Article and Find Full Text PDFIEEE Trans Neural Netw Learn Syst
November 2024
Quantizing neural network is an efficient model compression technique that converts weights and activations from floating-point to integer. However, existing model quantization methods are primarily designed for high-level visual tasks. They do not sufficiently consider the unique characteristics of feature distribution in image super-resolution (SR) reconstruction models.
View Article and Find Full Text PDFIntroduction: To investigate the effect of different levels of early intraocular pressure (IOP) on long-term outcomes of patients with primary open-angle glaucoma (POAG) who were treated with primary trabeculectomy.
Methods: This was a retrospective cohort study, with a total of 74 patients (90 eyes) with primary open-angle glaucoma (POAG) who were treated with trabeculectomy surgery at a single center from 2021 to 2022. Based on IOP at 1 day after surgery, they were divided into the high IOP group (≥ 15mmHg) and the low IOP group (< 15mmHg).
Pancreatic cancer is an aggressive malignancy with a dismal prognosis and limited therapeutic options. Adoptive cell therapy, which involves isolating and activating a patient's own immune cells, such as tumor-infiltrating lymphocytes (TILs), before re-infusing them, represents a promising experimental approach. However, techniques for adoptive cell transfer in preclinical pancreatic cancer models are not well established.
View Article and Find Full Text PDFAsia Pac J Ophthalmol (Phila)
January 2025
To analyze the treatment modalities and trends for neovascular glaucoma (NVG) over the past 10 years, we conducted a retrospective analysis at Zhongshan Ophthalmic Center on 1331 NVG inpatients who received 1459 treatments for 1383 eyes between January 1, 2012, and December 31, 2021. Over time, we observed a progressive annual increase in both the number of patients and the volume of surgeries for NVG, with an annual percentage change (APC) of 10.23 % (95 % confidence interval [CI]: 5.
View Article and Find Full Text PDFThe variants of DEtection TRansformer (DETRs) have achieved impressive performance in general object detection. However, they suffer notable performance degradation in scenarios involving crowded pedestrian detection. This decline primarily occurs during the training phase, where DETRs are constrained solely by pedestrian labels.
View Article and Find Full Text PDFIEEE Trans Neural Netw Learn Syst
October 2024
Recent blind super-resolution (BSR) methods are explored to handle unknown degradations and achieve impressive performance. However, the prevailing assumption in most BSR methods is the spatial invariance of degradation kernels across the entire image, which leads to significant performance declines when faced with spatially variant degradations caused by object motion or defocusing. Additionally, these methods do not account for the human visual system's tendency to focus differently on areas of varying perceptual difficulty, as they uniformly process each pixel during reconstruction.
View Article and Find Full Text PDFIn the field of computer-aided medical diagnosis, it is crucial to adapt medical image segmentation to limited computing resources. There is tremendous value in developing accurate, real-time vision processing models that require minimal computational resources. When building lightweight models, there is always a trade-off between computational cost and segmentation performance.
View Article and Find Full Text PDFBackground: Glaucoma is the most common cause of irreversible blindness, and gut microbiota (GM) is associated with glaucoma. Whether this association represents a causal role remains unknown. This study aims to assess the potential association and causal link between GM and various forms of glaucoma, emphasising the need for cautious interpretation of the strength of these associations.
View Article and Find Full Text PDFIEEE Trans Image Process
October 2024
The true label plays an important role in semi-supervised medical image segmentation (SSMIS) because it can provide the most accurate supervision information when the label is limited. The popular SSMIS method trains labeled and unlabeled data separately, and the unlabeled data cannot be directly supervised by the true label. This limits the contribution of labels to model training.
View Article and Find Full Text PDFMost few-shot learning methods employ either adaptive approaches or parameter amortization techniques. However, their reliance on pre-trained models presents a significant vulnerability. When an attacker's trigger activates a hidden backdoor, it may result in the misclassification of images, profoundly affecting the model's performance.
View Article and Find Full Text PDFPrcis: This research presents the burden and clinical characteristics of NVG in Zhongshan Ophthalmic Center, employing the most extensive sample size and the longest uninterrupted temporal duration so far, which may provide a theoretical reference for the effective prevention and diagnosis of NVG.
Purpose: To summarize the burden and clinical characteristics of neovascular glaucoma (NVG) in a major tertiary care center in China.
Methods: The clinical data of NVG patients in Zhongshan Ophthalmic Center (ZOC) between 2012 and 2021 were collected retrospectively, including their age, sex, the affected eye, best-corrected visual acuity (BCVA), intraocular pressure (IOP), clinical stage and etiology.
IEEE Trans Image Process
September 2024
The potential vulnerability of deep neural networks and the complexity of pedestrian images, greatly limits the application of person re-identification techniques in the field of smart security. Current attack methods often focus on generating carefully crafted adversarial samples or only disrupting the metric distances between targets and similar pedestrians. However, both aspects are crucial for evaluating the security of methods adapted for person re-identification tasks.
View Article and Find Full Text PDFWith the rapid and continuous development of AIGC, It is becoming increasingly difficult to distinguish between real and forged facial images, which calls for efficient forgery detection systems. Although many detection methods have noticed the importance of local artifacts, there has been a lack of in-depth discussion regarding the selection of locations and their effective utilization. Besides, the traditional image augmentation methods that are widely used have limited improvements for forgery detection tasks and require more specialized augmentation methods specifically designed for forgery detection tasks.
View Article and Find Full Text PDF