In an era where personal photos are easily leaked and collected, face de-identification is a crucial method for protecting identity privacy. However, current face de-identification techniques face challenges in preserving attribute details and often produce anonymized results with reduced realistic. These shortcomings are particularly evident when handling occlusions, frequently resulting in noticeable editing artifacts. Our primary finding in this work is that simultaneous training of identity disentanglement and anonymization hinders their respective effectiveness. Therefore, we propose “Disentangle Before Anonymize”, a novel two-stage Framework (DBAF) designed for attribute-preserved and occlusion-robust de-identification. This framework includes a Contrastive Identity Disentanglement (CID) module and a Key-authorized Reversible Identity Anonymization (KRIA) module, achieving faithful attribute preservation and high-quality identity anonymization edits. Additionally, we introduce a Multi-scale Attentional Attribute Retention (MAAR) module to address the issue of reduced anonymization quality under occlusions. Extensive experiments demonstrate that our method outperforms state-of-the-art de-identification approaches, delivering superior quality, enhanced detail fidelity, improved attribute preservation performance, and greater robustness to occlusions. The code ispublicly available at: https://github.com/mrzhu-cool/DBAF.

Privacy protection has become a top priority due to the widespread collection and misuse of personal data. Anonymization and visual identity information hiding are two crucial tasks in face privacy protection, both striving to alter identifying characteristics from face images to prevent privacy information leakage. However, the goals of the two are not entirely the same. Consequently, training a model to simultaneously perform both tasks proves challenging. In this paper, we propose Diff-Privacy, a novel face privacy protection method based on diffusion models that unifies the task of anonymization and visual identity information hiding. Specifically, we present a Multi-Scale image Inversion module (MSI) that, through training, generates a set of Stable Diffusion (SD) format conditional embeddings for the original image. With these conditional embeddings, we design corresponding embedding scheduling strategies and formulate distinct energy functions during the inference process to achieve anonymization and visual identity information hiding, respectively. Extensive experiments demonstrate the effectiveness of the proposed method in protecting face privacy.

Breast cancer leads to the top cause of death among women worldwide. Early detection of breast cancer is the most effective way to reduce the risk of death and increase the likelihood of survival. Breast ultrasound imaging is an essential test for early detection but its accurate evaluation is difficult due to the limited number of experienced sonographers. So the computer-aided system for breast cancer diagnosis on ultrasound images is vitally necessary. Recent breast cancer diagnosis methods are mostly developed by improving or transferring visual deep models to breast cancer diagnosis. These methods ignored the characteristics of breast cancer on ultrasound images. Some methods fuse the pre-defined region of interest (ROI) to adapt the characteristics of ultrasound images but cannot diagnose those samples whose ROIs are not defined. In this paper, we propose a novel framework, ROI Extraction and Adaptive Fusion (REAF), for breast cancer diagnosis on ultrasound images. To make the framework be applied to the samples without pre-defined ROIs as well as incorporate the characteristics of breast cancer on ultrasound images, the proposed REAF firstly extracts the ROI of breast tumor areas as a confidence degree map. Then we propose an adaptive fusion method to fuse the extracted ROI into the downstream diagnostic model. In addition, we propose a pair augmentation method to increase the variety of samples for enhancing the generalization of the proposed REAF. The experimental results demonstrate that the REAF surpasses state-of-the-art visual classification models and breast cancer methods. For the evaluation of the REAF, the AUC reaches 95.52%, the accuracy reaches 88.97%, the specificity reaches 92.86%, the precision reaches 89.43%, the recall reaches 86.82% and the f1-score reaches 88.05%.

Acne Vulgaris seriously affects people’s daily life. In this paper, we propose a face acne grading framework which is a new paradigm to solve the image classification problem where the number and type of small objects are the evidence. This framework includes two components: prior knowledge extraction and prior knowledge guided network. The prior knowledge extraction uses an excellent segmentation method to predict the lesion areas as prior knowledge. The prior knowledge guided network fuses the prior knowledge and its corresponding image to grade the severity. The experiment results demonstrate that our framework achieves the state-of-the-art and diagnosis level of dermatologists.

The collection and publication of medical images on the face are quite difficult because of the invasion of privacy. Meanwhile, it takes a major expenditure of time and effort to manually label large-scale face images covered with s o many fine skin lesions. In this work, a multi-class object large-scale image inpainting model Class-Guided PG-GAN (CGPG-GAN) is proposed and its application in boosting downstream model performances is explored. This model is applied on face acne lesion inpainting where the image size is very large and missing areas are different types of lesions. The experiment results show that our method is superior to some existing methods and can improve the performance of downstream diagnosis remarkably.