Medical anomaly detection is challenged by the scarcity and diversity of abnormal samples and the lack of precise annotations, limiting the scalability of supervised methods. To address this, we propose FMA-GEN, a novel diffusion-based framework for few-shot, multi-conditional controllable medical anomaly generation and detection. Specifically, FMA-GEN first introduces a text-guided anomaly mask generator, allowing the creation of diverse and semantically meaningful masks. These masks, combined with anomaly embeddings and textual prompts, are used to condition the diffusion process, facilitating the synthesis of high-fidelity and controllable anomalous images. To ensure anatomical realism, we further design a boundary-aware blending module that fuses normal and abnormal regions along mask boundaries. Finally, in the downstream detection stage, we develop a semi-supervised learning scheme that leverages the generated samples to enhance anomaly representation. A mask-guided feature mining strategy is employed to highlight discriminative abnormal features while suppressing interference from normal regions. Extensive experiments on the BraTS and LiverCT datasets demonstrate that FMA-GEN generates realistic and diverse anomalies, leading to significant improvements in both anomaly detection and localization tasks. Our code are available at https://github.com/TytopiaAI/FMA-GEN.

The precise segmentation of lesions in contrast-enhanced ultrasound (CEUS) videos, especially during the peak enhancement phase, is crucial for early breast cancer diagnosis. However, the dynamic contrast patterns and subtle differences in CEUS images challenge traditional methods. To overcome this, we propose the CEUS-SAM network, a deep learning framework leveraging the Segment Anything Model (SAM) for enhanced lesion segmentation. Our approach first trains on conventional ultrasound (US) data, generating segmentation masks as prompts for CEUS images. A key innovation, the Image Fusion Module (IFM), integrates cross-modal and multi-scale features from US and CEUS, improving tissue differentiation and lesion detection. The CEUS-SAM network significantly reduces manual effort with single-point prompts and minimizes inter-observer variability. Using a breast CEUS dataset with 135 video sequences, our method achieves a Dice score of 78.6% and an IoU score of 66.6%. The code and dataset are available at https://github.com/2284650586/CEUS-SAM.

Self-supervised feature reconstruction methods have shown promising advances in industrial image anomaly de-tection and localization. Despite this progress, these meth-ods still face challenges in synthesizing realistic and di-verse anomaly samples, as well as addressing the feature redundancy and pre-training bias of pre-trained feature. In this work, we introduce RealNet, a feature reconstruction network with realistic synthetic anomaly and adaptive feature selection. It is incorporated with three key inno-vations: First, we propose Strength-controllable Diffusion Anomaly Synthesis (SDAS), a diffusion process-based syn-thesis strategy capable of generating samples with varying anomaly strengths that mimic the distribution of real anomalous samples. Second, we develop Anomaly-aware Features Selection (A FS), a method for selecting repre-sentative and discriminative pre-trained feature subsets to improve anomaly detection performance while controlling computational costs. Third, we introduce Reconstruction Residuals Selection (RRS), a strategy that adaptively selects discriminative residuals for comprehensive identification of anomalous regions across multiple levels of granularity. We assess RealNet onfour benchmark datasets, and our results demonstrate significant improvements in both Image AU-Rae and Pixel AUROC compared to the current state-of-the-art methods. The code, data, and models are available at https://github.com/cnulab/RealNet.

In this paper, we investigate the problem of prediction confidence in face and kinship verification. Most existing face and kinship verification methods focus on accuracy performance while ignoring confidence estimation for their prediction results. However, confidence estimation is essential for modeling reliability and trustworthiness in such high-risk tasks. To address this, we introduce an effective confidence measure that allows verification models to convert a similarity score into a confidence score for any given face pair. We further propose a confidence-calibrated approach, termed Angular Scaling Calibration (ASC). ASC is easy to implement and can be readily applied to existing verification models without model modifications, yielding accuracy-preserving and confidence-calibrated probabilistic verification models. In addition, we introduce the uncertainty in the calibrated confidence to boost the reliability and trustworthiness of the verification models in the presence of noisy data. To the best of our knowledge, our work presents the first comprehensive confidence-calibrated solution for modern face and kinship verification tasks. We conduct extensive experiments on four widely used face and kinship verification datasets, and the results demonstrate the effectiveness of our proposed approach. Code and models are available athttps://github.com/cnulab/ASC.

Illegal construction poses a safety hazard to both cities and people and affects the social stability and long-term stability of the country. Therefore, it is important to detect illegal buildings as early as possible. However, current illegal building detection methods generally suffer from either detection cycles or low detection accuracies. To solve these challenges, this study adopts an unusual method that detects illegal building objects to prevent illegal building behavior. A detection model, CRMNet, which is based on the anchor-free detection model CenterNet, and dataset for illegal building objects are proposed. ResNet50 is selected as the backbone for extracting futures after weighing the computational cost and detection accuracy. Furthermore, Mish, a new activation function, is used to improve the identification accuracy of illegal building objects. Experimental results show that the mean average precision (mAP) of the proposed detector on the illegal building object dataset reached 88.16%, which is higher than that of other popular object detection methods. Additionally, in contrast to mainstream target detection methods, the proposed detection method has fewer parameters and a higher detection accuracy, which can be better applied to mobile devices and smart devices.

While existing prediction models built on popular deep architectures have shown promising results in facial depression recognition, they still lack sufficient discriminative power due to the issues of 1) limited amount of labeled depression data for deep representation learning and, 2) large variation in facial expression across different persons of the same depression score and the subtle difference in facial expression across different depression levels. In this article, we formulate the facial depression recognition as a label distribution learning (LDL) problem, and propose a deep joint label distribution and metric learning (DJ-LDML) method to address these issues. In DJ-LDML, LDL exploits label relevance inherent in depression data to implicitly increase the amount of training data associated with each depression level without actually enlarging the dataset, while deep metric learning (DML) aims at learning a deep ordinal embedding with a specifically designed label-aware histogram loss, allowing semantics similarity between video sequences (described by ordinal labels) to be preserved for discriminative feature learning. The two learning modules in our DJ-LDML work collaboratively to enhance the representation ability and discriminative power of the deeply learned spatiotemporal feature, leading to improved depression prediction. We empirically evaluate our method on two benchmark datasets and the results demonstrate the effectiveness of our formulation.

Vision-based kinship recognition aims to determine whether the face images have a kin relation. Compared to traditional solutions, the vision-based kinship recognition methods have the advantages of lower cost and being easy to implement. Therefore, such technique can be widely employed in lots of scenarios including missing children search and automatic management of family album. The Recognizing Families in the Wild (RFIW) Data Challenge provides a platform for evaluation of different kinship recognition approaches with ranked results. We propose a supervised contrastive learning approach to address three different kinship recognition tracks (i.e., kinship verification, tri-subject verification, and large-scale search-and-retrieval) announced in the RFIW 2021 with the 2021 FG. Our results on three tracks of 2021 RFIW challenge achieve the highest ranking, which demonstrate the superiority of the proposed solution.

While encouraging results have been made so far to advance kinship verification by using facial images, learning a robust genetic similarity measure remains challenging, especially in the setting of general kinship verification, wherein the gender labels of the test samples are unknown in advance. In this paper we present a deep metric learning method with a carefully designed two-stream neural network to jointly learn a pair of deep embeddings for parent-child images. In particular, the deep embeddings are first modeled to explicitly consist of the common and individual components, and then two additional constraints are introduced in deep metric learning: 1) value-aware consistency on the common components, and 2) position-aware exclusivity on the individual components. The proposed hierarchical consistency-exclusivity regularization enables our deep metric learning to harness the sharable and complementary patterns inherent in parent-child images. Empirically, we show improved performance over state of the art metric learning solutions to general kinship verification on two benchmarks.

In this paper, we propose a fast and accurate block-matching algorithm for motion estimation of human faces via Artificial Bee Colony (ABC) optimization. The mean square error (MSE) is often used as the matching metric in block matching, which, however, has the high computational cost in practice. By using ABC optimization, we introduce a novel and effective block-matching metric. We develop a block-matching algorithm based on the proposed matching metric to improve the motion estimation accuracy of human faces with lower computational cost. Experimental results show that our method could achieve significant improvements over state-of-the-art fast block matching methods for motion estimation, in terms of both estimation accuracy and computational complexity.