Related papers: VALD-MD: Visual Attribution via Latent Diffusion f…
Deep generative models have emerged as promising tools for detecting arbitrary anomalies in data, dispensing with the necessity for manual labelling. Recently, autoregressive transformers have achieved state-of-the-art performance for…
Lesion detection, symptom tracking, and visual explainability are central to real-world medical image analysis, yet current medical Vision-Language Models (VLMs) still lack mechanisms that translate their broad knowledge into clinically…
Text-to-image diffusion models have made significant progress in generating naturalistic images from textual inputs, and demonstrate the capacity to learn and represent complex visual-semantic relationships. While these diffusion models…
Counterfactual medical image generation effectively addresses data scarcity and enhances the interpretability of medical images. However, due to the complex and diverse pathological features of medical images and the imbalanced class…
Deploying video anomaly detection in practice is hampered by the scarcity and collection cost of real abnormal footage. We address this by training without any real abnormal videos while evaluating under the standard weakly supervised…
Long-tailed class distributions are pervasive in multi-class medical datasets and pose significant challenges for deep learning models which typically underperform on tail classes with limited samples. This limitation is particularly…
Unsupervised anomaly detection (UAD) in medical imaging is crucial for identifying pathological abnormalities without requiring extensive labeled data. However, existing diffusion-based UAD models rely solely on imaging features, limiting…
Deep learning-based image generation has seen significant advancements with diffusion models, notably improving the quality of generated images. Despite these developments, generating images with unseen characteristics beneficial for…
Artificial Intelligence (AI) based image analysis has an immense potential to support diagnostic histopathology, including cancer diagnostics. However, developing supervised AI methods requires large-scale annotated datasets. A potentially…
Latest methods for visual counterfactual explanations (VCE) harness the power of deep generative models to synthesize new examples of high-dimensional images of impressive quality. However, it is currently difficult to compare the…
We introduce Diffusion Active Learning, a novel approach that combines generative diffusion modeling with data-driven sequential experimental design to adaptively acquire data for inverse problems. Although broadly applicable, we focus on…
Single-view novel view synthesis (NVS), the task of generating images from new viewpoints based on a single reference image, is important but challenging in computer vision. Recent advancements in NVS have leveraged Denoising Diffusion…
We introduce Discrete Voxel Diffusion (DVD), a discrete diffusion framework to generate, assess, and edit sparse voxels for SLat (Structured LATent) based 3D generative pipelines. Although discrete diffusion has not generally displaced…
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…
Super Resolution (SR) plays a critical role in computer vision, particularly in medical imaging, where hardware and acquisition time constraints often result in low spatial and temporal resolution. While diffusion models have been applied…
Temporal volume images with 3D+t (4D) information are often used in medical imaging to statistically analyze temporal dynamics or capture disease progression. Although deep-learning-based generative models for natural images have been…
Dual-view mammography, including craniocaudal (CC) and mediolateral oblique (MLO) projections, offers complementary anatomical views crucial for breast cancer diagnosis. However, in real-world clinical workflows, one view may be missing,…
Image-to-Image translation models can help mitigate various challenges inherent to medical image acquisition. Latent diffusion models (LDMs) leverage efficient learning in compressed latent space and constitute the core of state-of-the-art…
Based on the Denoising Diffusion Probabilistic Model (DDPM), medical image segmentation can be described as a conditional image generation task, which allows to compute pixel-wise uncertainty maps of the segmentation and allows an implicit…
Efficiently utilizing discriminative features is crucial for convolutional neural networks to achieve remarkable performance in medical image segmentation and is also important for model generalization across multiple domains, where letting…