Stylizing ViT: Anatomy-Preserving Instance Style Transfer for Domain Generalization

Deep learning models in medical image analysis often struggle with generalizability across domains and demographic groups due to data heterogeneity and scarcity. Traditional augmentation improves robustness, but fails under substantial domain shifts. Recent advances in stylistic augmentation enhance domain generalization by varying image styles but fall short in terms of style diversity or by introducing artifacts into the generated images. To address these limitations, we propose Stylizing ViT, a novel Vision Transformer encoder that utilizes weight-shared attention blocks for both self- and cross-attention. This design allows the same attention block to maintain anatomical consistency through self-attention while performing style transfer via cross-attention. We assess the effectiveness of our method for domain generalization by employing it for data augmentation on three distinct image classification tasks in the context of histopathology and dermatology. Results demonstrate an improved robustness (up to +13% accuracy) over the state of the art while generating perceptually convincing images without artifacts. Additionally, we show that Stylizing ViT is effective beyond training, achieving a 17% performance improvement during inference when used for test-time augmentation. The source code is available at https://github.com/sdoerrich97/stylizing-vit .

Training-Free Text-to-Image Compositional Food Generation via Prompt Grafting

Real-world meal images often contain multiple food items, making reliable compositional food image generation important for applications such as image-based dietary assessment, where multi-food data augmentation is needed, and recipe visualization. However, modern text-to-image diffusion models struggle to generate accurate multi-food images due to object entanglement, where adjacent foods (e.g., rice and soup) fuse together because many foods do not have clear boundaries. To address this challenge, we introduce Prompt Grafting (PG), a training-free framework that combines explicit spatial cues in text with implicit layout guidance during sampling. PG runs a two-stage process where a layout prompt first establishes distinct regions and the target prompt is grafted once layout formation stabilizes. The framework enables food entanglement control: users can specify which food items should remain separated or be intentionally mixed by editing the arrangement of layouts. Across two food datasets, our method significantly improves the presence of target objects and provides qualitative evidence of controllable separation.

Making medical vision-language models think causally across modalities with retrieval-augmented cross-modal reasoning

Medical vision-language models (VLMs) achieve strong performance in diagnostic reporting and image-text alignment, yet their underlying reasoning mechanisms remain fundamentally correlational, exhibiting reliance on superficial statistical associations that fail to capture the causal pathophysiological mechanisms central to clinical decision-making. This limitation makes them fragile, prone to hallucinations, and sensitive to dataset biases. Retrieval-augmented generation (RAG) offers a partial remedy by grounding predictions in external knowledge. However, conventional RAG depends on semantic similarity, introducing new spurious correlations. We propose Multimodal Causal Retrieval-Augmented Generation, a framework that integrates causal inference principles with multimodal retrieval. It retrieves clinically relevant exemplars and causal graphs from external sources, conditioning model reasoning on counterfactual and interventional evidence rather than correlations alone. Applied to radiology report generation, diagnosis prediction, and visual question answering, it improves factual accuracy, robustness to distribution shifts, and interpretability. Our results highlight causal retrieval as a scalable path toward medical VLMs that think beyond pattern matching, enabling trustworthy multimodal reasoning in high-stakes clinical settings.

A Source-Free Approach for Domain Adaptation via Multiview Image Transformation and Latent Space Consistency

Domain adaptation (DA) addresses the challenge of transferring knowledge from a source domain to a target domain where image data distributions may differ. Existing DA methods often require access to source domain data, adversarial training, or complex pseudo-labeling techniques, which are computationally expensive. To address these challenges, this paper introduces a novel source-free domain adaptation method. It is the first approach to use multiview augmentation and latent space consistency techniques to learn domain-invariant features directly from the target domain. Our method eliminates the need for source-target alignment or pseudo-label refinement by learning transferable representations solely from the target domain by enforcing consistency between multiple augmented views in the latent space. Additionally, the method ensures consistency in the learned features by generating multiple augmented views of target domain data and minimizing the distance between their feature representations in the latent space. We also introduce a ConvNeXt-based encoder and design a loss function that combines classification and consistency objectives to drive effective adaptation directly from the target domain. The proposed model achieves an average classification accuracy of 90. 72\%, 84\%, and 97. 12\% in Office-31, Office-Home and Office-Caltech datasets, respectively. Further evaluations confirm that our study improves existing methods by an average classification accuracy increment of +1.23\%, +7.26\%, and +1.77\% on the respective datasets.

A Systemic Evaluation of Multimodal RAG Privacy

The growing adoption of multimodal Retrieval-Augmented Generation (mRAG) pipelines for vision-centric tasks (e.g. visual QA) introduces important privacy challenges. In particular, while mRAG provides a practical capability to connect private datasets to improve model performance, it risks the leakage of private information from these datasets during inference. In this paper, we perform an empirical study to analyze the privacy risks inherent in the mRAG pipeline observed through standard model prompting. Specifically, we implement a case study that attempts to infer the inclusion of a visual asset, e.g. image, in the mRAG, and if present leak the metadata, e.g. caption, related to it. Our findings highlight the need for privacy-preserving mechanisms and motivate future research on mRAG privacy.

Scale-Aware Self-Supervised Learning for Segmentation of Small and Sparse Structures

Self-supervised learning (SSL) has emerged as a powerful strategy for representation learning under limited annotation regimes, yet its effectiveness remains highly sensitive to many factors, especially the nature of the target task. In segmentation, existing pipelines are typically tuned to large, homogeneous regions, but their performance drops when objects are small, sparse, or locally irregular. In this work, we propose a scale-aware SSL adaptation that integrates small-window cropping into the augmentation pipeline, zooming in on fine-scale structures during pretraining. We evaluate this approach across two domains with markedly different data modalities: seismic imaging, where the goal is to segment sparse faults, and neuroimaging, where the task is to delineate small cellular structures. In both settings, our method yields consistent improvements over standard and state-of-the-art baselines under label constraints, improving accuracy by up to 13% for fault segmentation and 5% for cell delineation. In contrast, large-scale features such as seismic facies or tissue regions see little benefit, underscoring that the value of SSL depends critically on the scale of the target objects. Our findings highlight the need to align SSL design with object size and sparsity, offering a general principle for buil ding more effective representation learning pipelines across scientific imaging domains.

DSTCS: Dual-Student Teacher Framework with Segment Anything Model for Semi-Supervised Pubic Symphysis Fetal Head Segmentation

Segmentation of the pubic symphysis and fetal head (PSFH) is a critical procedure in intrapartum monitoring and is essential for evaluating labor progression and identifying potential delivery complications. However, achieving accurate segmentation remains a significant challenge due to class imbalance, ambiguous boundaries, and noise interference in ultrasound images, compounded by the scarcity of high-quality annotated data. Current research on PSFH segmentation predominantly relies on CNN and Transformer architectures, leaving the potential of more powerful models underexplored. In this work, we propose a Dual-Student and Teacher framework combining CNN and SAM (DSTCS), which integrates the Segment Anything Model (SAM) into a dual student-teacher architecture. A cooperative learning mechanism between the CNN and SAM branches significantly improves segmentation accuracy. The proposed scheme also incorporates a specialized data augmentation strategy optimized for boundary processing and a novel loss function. Extensive experiments on the MICCAI 2023 and 2024 PSFH segmentation benchmarks demonstrate that our method exhibits superior robustness and significantly outperforms existing techniques, providing a reliable segmentation tool for clinical practice.

Diffusion Model-Based Data Augmentation for Enhanced Neuron Segmentation

Neuron segmentation in electron microscopy (EM) aims to reconstruct the complete neuronal connectome; however, current deep learning-based methods are limited by their reliance on large-scale training data and extensive, time-consuming manual annotations. Traditional methods augment the training set through geometric and photometric transformations; however, the generated samples remain highly correlated with the original images and lack structural diversity. To address this limitation, we propose a diffusion-based data augmentation framework capable of generating diverse and structurally plausible image-label pairs for neuron segmentation. Specifically, the framework employs a resolution-aware conditional diffusion model with multi-scale conditioning and EM resolution priors to enable voxel-level image synthesis from 3D masks. It further incorporates a biology-guided mask remodeling module that produces augmented masks with enhanced structural realism. Together, these components effectively enrich the training set and improve segmentation performance. On the AC3 and AC4 datasets under low-annotation regimes, our method improves the ARAND metric by 32.1% and 30.7%, respectively, when combined with two different post-processing methods. Our code is available at https://github.com/HeadLiuYun/NeuroDiff.

RAICL: Retrieval-Augmented In-Context Learning for Vision-Language-Model Based EEG Seizure Detection

Electroencephalogram (EEG) decoding is a critical component of medical diagnostics, rehabilitation engineering, and brain-computer interfaces. However, contemporary decoding methodologies remain heavily dependent on task-specific datasets to train specialized neural network architectures. Consequently, limited data availability impedes the development of generalizable large brain decoding models. In this work, we propose a paradigm shift from conventional signal-based decoding by leveraging large-scale vision-language models (VLMs) to analyze EEG waveform plots. By converting multivariate EEG signals into stacked waveform images and integrating neuroscience domain expertise into textual prompts, we demonstrate that foundational VLMs can effectively differentiate between different patterns in the human brain. To address the inherent non-stationarity of EEG signals, we introduce a Retrieval-Augmented In-Context Learning (RAICL) approach, which dynamically selects the most representative and relevant few-shot examples to condition the autoregressive outputs of the VLM. Experiments on EEG-based seizure detection indicate that state-of-the-art VLMs under RAICL achieved better or comparable performance with traditional time series based approaches. These findings suggest a new direction in physiological signal processing that effectively bridges the modalities of vision, language, and neural activities. Furthermore, the utilization of off-the-shelf VLMs, without the need for retraining or downstream architecture construction, offers a readily deployable solution for clinical applications.

A Novel Transfer Learning Approach for Mental Stability Classification from Voice Signal

This study presents a novel transfer learning approach and data augmentation technique for mental stability classification using human voice signals and addresses the challenges associated with limited data availability. Convolutional neural networks (CNNs) have been employed to analyse spectrogram images generated from voice recordings. Three CNN architectures, VGG16, InceptionV3, and DenseNet121, were evaluated across three experimental phases: training on non-augmented data, augmented data, and transfer learning. This proposed transfer learning approach involves pre-training models on the augmented dataset and fine-tuning them on the non-augmented dataset while ensuring strict data separation to prevent data leakage. The results demonstrate significant improvements in classification performance compared to the baseline approach. Among three CNN architectures, DenseNet121 achieved the highest accuracy of 94% and an AUC score of 99% using the proposed transfer learning approach. This finding highlights the effectiveness of combining data augmentation and transfer learning to enhance CNN-based classification of mental stability using voice spectrograms, offering a promising non-invasive tool for mental health diagnostics.