A simultaneous enhancement of accuracy and diversity of predictions remains a challenge in ambiguous medical image segmentation (AMIS) due to the inherent trade-offs. While truncated diffusion probabilistic models (TDPMs) hold strong potential with a paradigm optimization, existing TDPMs suffer from entangled accuracy and diversity of predictions with insufficient fidelity and plausibility. To address the aforementioned challenges, we propose Ambiguity-aware Truncated Flow Matching (ATFM), which introduces a novel inference paradigm and dedicated model components. Firstly, we propose Data-Hierarchical Inference, a redefinition of AMIS-specific inference paradigm, which enhances accuracy and diversity at data-distribution and data-sample level, respectively, for an effective disentanglement. Secondly, Gaussian Truncation Representation (GTR) is introduced to enhance both fidelity of predictions and reliability of truncation distribution, by explicitly modeling it as a Gaussian distribution at Ttrunc instead of using sampling-based approximations. Thirdly, Segmentation Flow Matching (SFM) is proposed to enhance the plausibility of diverse predictions by extending semantic-aware flow transformation in Flow Matching (FM). Comprehensive evaluations on LIDC and ISIC3 datasets demonstrate that ATFM outperforms SOTA methods and simultaneously achieves a more efficient inference. ATFM improves GED and HM-IoU by up to 12% and 7.3% compared to advanced methods.

With the growing global threat of coronary artery disease (CAD), automated CAD diagnosis techniques based on coronary CT angiography (CCTA) have been developed. However, their clinical applicability remains limited due to the heterogeneity of stenosis and plaque attributes, as well as confounders within the causal relationships of CAD diagnosis. This work introduces the Attribute-Decoupled Intervention Network (ADI-Net), a confounder-free CAD diagnosis framework designed for fine-grained analysis at both the artery and patient levels, aligning with real-world clinical practice. ADI-Net employs an attribute-decoupled representation that effectively captures the heterogeneous features of stenosis and plaque with differential constraints, enabling precise, fine-grained classification. Additionally, the dynamic-updating causal intervention continuously refines confounder banks and applies the Do-expression within a complete causality, ensuring comprehensive, cross-level assessments. Experiments on CCTA datasets from three clinical centers demonstrate that ADI-Net outperforms state-of-the-art methods in cross-level, fine-grained CAD diagnosis, exhibiting superior robustness, domain adaptability, and data efficiency.

In image generation, Schrödinger Bridge (SB)-based methods theoretically enhance the efficiency and quality compared to the diffusion models by finding the least costly path between two distributions. However, they are computationally expensive and time-consuming when applied to complex image data. The reason is that they focus on fitting globally optimal paths in high-dimensional spaces, directly generating images as next step on the path using complex networks through self-supervised training, which typically results in a gap with the global optimum. Meanwhile, most diffusion models are in the same path subspace generated by weights fA(t) and fB(t), as they follow the paradigm (xt= fA(t)xImg+ fB(t)ϵ). To address the limitations of SB-based methods, this paper proposes for the first time to find local Diffusion Schrödinger Bridges (LDSB) in the diffusion path subspace, which strengthens the connection between the SB problem and diffusion models. Specifically, our method optimizes the diffusion paths using Kolmogorov-Arnold Network (KAN), which has the advantage of resistance to forgetting and continuous output. The experiment shows that our LDSB significantly improves the quality and efficiency of image generation using the same pretrained denoising network and the KAN for optimising is only less than 0.1MB. The FID metric is reduced by more than 15%, especially with a reduction of 48.50% when NFE of DDIM is 5 for the CelebA dataset. Code is available at https://github.com/PerceptionComputingLab/LDSB.

Cross-Domain Few-Shot Object Detection (CD-FSOD) aims to detect novel objects with only a handful of labeled samples from previously unseen domains. While data augmentation and generative methods have shown promise in few-shot learning, their effectiveness for CD-FSOD remains unclear due to the need for both visual realism and domain alignment. Existing strategies, such as copy-paste augmentation and text-to-image generation, often fail to preserve the correct object category or produce backgrounds coherent with the target domain, making them non-trivial to apply directly to CD-FSOD. To address these challenges, we propose Domain-RAG, a training-free, retrieval-guided compositional image generation framework tailored for CD-FSOD. Domain-RAG consists of three stages: domain-aware background retrieval, domain-guided background generation, and foreground-background composition. Specifically, the input image is first decomposed into foreground and background regions. We then retrieve semantically and stylistically similar images to guide a generative model in synthesizing a new background, conditioned on both the original and retrieved contexts. Finally, the preserved foreground is composed with the newly generated domain-aligned background to form the generated image. Without requiring any additional supervision or training, Domain-RAG produces high-quality, domain-consistent samples across diverse tasks, including CD-FSOD, remote sensing FSOD, and camouflaged FSOD. Extensive experiments show consistent improvements over strong baselines and establish new state-of-the-art results. Codes will be released upon acceptance.The source code and instructions are available at https://github.com/LiYu0524/Domain-RAG.

Bias fields inevitably degrade MRI that seriously interferes the diagnosis of physicians for accurate analysis, and removing it is a crucial image analysis task. Generative models (such as GANs) are used for bias field correction, and outperform traditional methods, however are hindered by the high cost of data annotation and instability during training. Recently, the diffusion-based methods have excelled over GANs in many applications, and they are powerful in removing noise from images, while the bias field can be regarded as a smooth noise. However, it is a challenge to directly apply to 3D bias field correction due to sampling inefficiency, the heavy computational demand, and implicit correction process. We propose a Memory-Efficient Multivariate Gaussian Bias Diffusion Model (MeMGB-Diff) that is an explicit, sampling, and memory both efficient diffusion model for 3D bias field correction without using clinical labels. MeMGB-Diff extends the diffusion models to multivariate Gaussian and models the bias field as a multivariate Gaussian variable, allowing direct diffusion and removal of the 3D bias fields without Gaussian noise. For memory efficiency, MeMGB-Diff performs diffusion model in smaller readable image domain at the expense of a negligible accuracy loss, based on the strong correlation among adjacent voxels of bias field. We also propose a loss function to mainly learn the intensity trend, which mainly causes the inhomogeneity of MRI, and effectively increases the correction accuracy. For comprehensive performance comparison, we propose a synthetic method for generating more varied bias fields during testing. Both quantitative and qualitative assessments on synthetic and clinical data confirm the high fidelity and uniform intensity of our results. MeMGB-Diff reduces data size by 64 times to use less memory, improves sampling efficiency by more than 10 times compared to other diffusion-based methods, and achieves optimal metrics, including SSIM, PSNR, COCO, and CV for various tissues. Hence, our MeMGB-Diff is a state-of-the-art (SOTA) method for 3D bias field correction.

Out-of-Distribution (OOD) detection aims to address the excessive confidence prediction by neural networks by triggering an alert when the input sample deviates significantly from the training distribution (in-distribution), indicating that the output may not be reliable. Current OOD detection approaches explore all kinds of cues to identify OOD data, such as finding irregular patterns in the feature space, logit space, gradient space, or the raw image space. Surprisingly, we observe a linear trend between the OOD score produced by current OOD detection algorithms and the network features on several datasets. We conduct a thorough investigation, theoretically and empirically, to analyze and understand the meaning of such a linear trend in OOD detection. This paper proposes a Robust Test-time Linear method (RTL) to utilize such linear trends like a ‘free lunch’ when we have a batch of data to perform OOD detection. By using a simple linear regression as a test time adaptation, we can make a more precise OOD prediction. We further propose an online variant of the proposed method, which achieves promising performance and is more practical for real applications. Theoretical analysis is given to prove the effectiveness of our methods. Extensive experiments on several OOD datasets show the efficacy of RTL for OOD detection tasks, significantly improving the results of base OOD detectors. Project will be available at https://github.com/kfan21/RTL.

With the progression of artificial intelligence, there has been substantial advancement in autonomous driving technology. However, even the most advanced systems may confront failures in certain corner cases, necessitating enhanced analytical approaches. Traditional approaches focused on the numerical analysis of isolated sensor data, are often insufficient for deriving meaningful insights in such situations. To address this inadequacy, we propose a visual analytics approach, crafted to aid domain experts in performing analyses and extracting system improvements from cases with unexpected behaviors. This approach intricately integrates extensive driving scenarios and low-level module behaviors into the autonomous driving decision-making process, utilizing rich visualizations and an interface for interactive exploration and systematic synthesis of findings. Uniquely, our system opens the "black box" of modules in the decision-making pipeline during corner cases, taking into account both the overall decision-making pipeline and the fine-grained behaviors of the modules in the pipeline, setting our approach apart from previous works. To validate our system’s effectiveness, we perform two case studies, inviting domain experts for evaluation, and the results confirm our system’s efficacy in allowing experts to obtain crucial insights into autonomous driving systems.