Scribble supervision reduces annotation costs in multi-organ segmentation. However, its sparsity results in insufficient supervision for most regions and inadequate feature learning in hard areas (e.g., organ boundaries). These hard areas cause model confirmation bias and high epistemic uncertainty, which existing methods fail to address. To overcome these core challenges, we propose an epistemic-driven hardness-adaptive focusing framework. This framework establishes a self-improving loop: quantified epistemic uncertainty guides hard sample generation, while hard sample learning and feature alignment jointly reduce epistemic uncertainty. Specifically, we first propose a phase-adaptive hardness-aware loss function to quantify epistemic uncertainty and generate dynamic hardness maps during training. Based on these maps, we employ a distribution-divergence-aware copy-paste operation to create hard samples, which are progressively incorporated into learning to reduce epistemic uncertainty. Furthermore, we introduce feature distribution alignment to mitigate bias and epistemic uncertainty by aligning organ-specific hard regions with global features. Extensive experiments on multi-organ CT and ultrasound datasets demonstrate the competitiveness and effectiveness of our method. The framework's generalizability and robustness are further validated under cross-dataset and noise-corrupted scenarios. This work offers a practical solution for clinical applications where annotation efficiency is critical.

Despite substantial progress in promoting fairness in high-stake applications using machine learning models, existing methods often modify the training process, such as through regularizers or other interventions, but lack formal guarantees that fairness achieved during training will generalize to unseen data. Although overfitting with respect to prediction performance has been extensively studied, overfitting in terms of fairness loss has received far less attention. This paper proposes a theoretical framework for analyzing fairness generalization error through an information-theoretic lens. Our novel bounding technique is based on Efron–Stein inequality, which allows us to derive tight information-theoretic fairness generalization bounds with both Mutual Information (MI) and Conditional Mutual Information (CMI). Our empirical results validate the tightness and practical relevance of these bounds across diverse fairness-aware learning algorithms. Our framework offers valuable insights to guide the design of algorithms improving fairness generalization.

Semantic segmentation of ultrasound (US) images with deep learning has played a crucial role in computer-aided disease screening, diagnosis and prognosis. However, due to the scarcity of US images and small field of view, resulting segmentation models are tailored for a specific single organ and may lack robustness, overlooking correlations among anatomical structures of multiple organs. To address these challenges, we propose the Multi-Organ FOundation (MOFO) model for universal US image segmentation. The MOFO is optimized jointly from multiple organs across various anatomical regions to overcome the data scarcity and explore correlations between multiple organs. The MOFO extracts organ-invariant representations from US images. Simultaneously, the task prompt is employed to refine organ-specific representations for segmentation predictions. Moreover, the anatomical prior is incorporated to enhance the consistency of the anatomical structures. A multi-organ US database with segmentation labels, comprising 7039 images from 10 organs across various regions of the human body, has been established to develop and evaluate our model. Results demonstrate that the MOFO outperforms single-organ methods in terms of the Dice coefficient, 95% Hausdorff distance and average symmetric surface distance with statistically sufficient margins. Our experiments in multi-organ universal segmentation for US images serve as a pioneering exploration of improving segmentation performance by leveraging semantic and anatomical relationships within US images of multiple organs.

Double-descent refers to the unexpected drop in test loss of a learning algorithm beyond an interpolating threshold with over-parameterization, which is not predicted by information criteria in their classical forms due to the limitations in the standard asymptotic approach. We update these analyses using the information risk minimization framework and provide Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) for models learned by the Gibbs algorithm. Notably, the penalty terms for the Gibbs-based AIC and BIC correspond to specific information measures, i.e., symmetrized KL information and KL divergence. We extend this information-theoretic analysis to over-parameterized models by providing two different Gibbs-based BICs to compute the marginal likelihood of random feature models in the regime where the number of parameters $p$ and the number of samples $n$ tend to infinity, with $p/n$ fixed. Our experiments demonstrate that the Gibbs-based BIC can select the high-dimensional model and reveal the mismatch between marginal likelihood and population risk in the over-parameterized regime, providing new insights to understand double-descent.

Vehicle Re-Identification (ReID) aims to find images of the same vehicle from different videos. It remains a challenging task in the video analysis field due to the huge appearance discrepancy of the same vehicle in cross-view matching and the subtle difference of different similar vehicles in same-view matching. In this paper, we propose a Co-occurrence Attention Net (CAN) to deal with these two challenges. Specifically, CAN consists of two branches, a main branch and an aware branch. The main branch is in charge of extracting global features that are consistent in most views. This feature encodes holistic information such as color and pose, however, it can not handle cross/same-view hard cases, as shown in Fig.1. Therefore, the aware branch is designed to focus on the local details and viewpoint information, which can become an important complement for those hard cases. Considering that the positions of local areas such as wheels and logos change with the viewpoint, Aware Attention Module is introduced to find the hidden relationship among local areas and seamlessly combine the viewpoint information simultaneously. Then, CAN is trained by a partition-and-reunion-based loss, which can narrow the intra-class distance and increase the inter-class distance. Further, an adaptive co-occurrence view emphasize strategy is adopted to fully utilize the learned features. Experimental results on three widely used datasets including VeRi-776, VehicleID and VERI-Wild demonstrate the effectiveness of our method and competitive performance with other state-of-the-art methods.

The accurate segmentation of prostate region in magnetic resonance imaging (MRI) can provide reliable basis for artificially intelligent diagnosis of prostate cancer. Transformer-based models have been increasingly used in image analysis due to their ability to acquire long-term global contextual features. Although Transformer can provide feature representations of the overall appearance and contour representations at long distance, it does not perform well on small-scale datasets of prostate MRI due to its insensitivity to local variation such as the heterogeneity of the grayscale intensities in the peripheral zone and transition zone across patients; meanwhile, the convolutional neural network (CNN) could retain these local features well. Therefore, a robust prostate segmentation model that can aggregate the characteristics of CNN and Transformer is desired. In this work, a U-shaped network based on the convolution coupled Transformer is proposed for segmentation of peripheral and transition zones in prostate MRI, named the convolution coupled Transformer U-Net (CCT-Unet). The convolutional embedding block is first designed for encoding high-resolution input to retain the edge detail of the image. Then the convolution coupled Transformer block is proposed to enhance the ability of local feature extraction and capture long-term correlation that encompass anatomical information. The feature conversion module is also proposed to alleviate the semantic gap in the process of jumping connection. Extensive experiments have been conducted to compare our CCT-Unet with several state-of-the-art methods on both the ProstateX open dataset and the self-bulit Huashan dataset, and the results have consistently shown the accuracy and robustness of our CCT-Unet in MRI prostate segmentation.

Vehicle Re-Identification (ReID) aims to retrieve images of vehicles with the same identity from different scenarios. It is a challenging task due to the large intra-identity discrepancy caused by viewpoint variations and the subtle inter-identity difference produced by similar appearances. In this paper, we propose a Viewpoint-Aware Loss (VAL) function to deal with these challenges. Specifically, we propose partition and reunion operations in VAL, which significantly shrinks the intra-identity distance and acquires viewpoint-invariant representations. In addition, we embed a multi-decision boundary mechanism in VAL. It contributes to enlarging the inter-identity distance. A comprehensive evaluation on two benchmarks shows the superiority of our method in contrast to a series of existing state-of-the-arts.