Related papers: Towards Scalable Language-Image Pre-training for 3…

Deep learning based computed tomography (CT) reconstruction has demonstrated outstanding performance on simulated 2D low-dose CT data. This applies in particular to domain adapted neural networks, which incorporate a handcrafted physics…

Contrastive Language-Image Pretraining (CLIP) has emerged as a novel paradigm to learn visual models from language supervision. While researchers continue to push the frontier of CLIP, reproducing these works remains challenging. This is…

Medical image segmentation is a cornerstone of computer-assisted diagnosis and treatment planning. While recent multimodal vision-language models have shown promise in enhancing semantic understanding through textual descriptions, their…

Recent advancements in pre-trained vision-language models like CLIP have enabled the task of open-vocabulary segmentation. CLIP demonstrates impressive zero-shot capabilities in various downstream tasks that require holistic image…

Medical image segmentation remains challenging due to limited annotations for training, ambiguous anatomical features, and domain shifts. While vision-language models such as CLIP offer strong cross-modal representations, their potential…

With the rise of medical foundation models and the growing availability of imaging data, scalable pretraining techniques offer a promising way to identify imaging biomarkers predictive of future disease risk. While current self-supervised…

We consider training classifiers for 3D medical images using only one binary label for the entire volume rather than a label for each 2D slice. In such weakly supervised settings, can we learn accurate classifiers for slice-level…

Recent work has shown that self-supervised pre-training leads to improvements over supervised learning on challenging visual recognition tasks. CLIP, an exciting new approach to learning with language supervision, demonstrates promising…

In modern large language models (LLMs), increasing the context length is crucial for improving comprehension and coherence in long-context, multi-modal, and retrieval-augmented language generation. While many recent transformer models…

Integrating functional magnetic resonance imaging (fMRI) connectivity data with phenotypic textual descriptors (e.g., disease label, demographic data) holds significant potential to advance our understanding of neurological conditions.…

The scarcity of annotated data has sparked significant interest in unsupervised pre-training methods that leverage medical reports as auxiliary signals for medical visual representation learning. However, existing research overlooks the…

Language-supervised pre-training has proven to be a valuable method for extracting semantically meaningful features from images, serving as a foundational element in multimodal systems within the computer vision and medical imaging domains.…

In the field of medical Vision-Language Pre-training (VLP), significant efforts have been devoted to deriving text and image features from both clinical reports and associated medical images. However, most existing methods may have…

Although fusion of information from multiple views of mammograms plays an important role to increase accuracy of breast cancer detection, developing multi-view mammograms-based computer-aided diagnosis (CAD) schemes still faces challenges…

Recent advancements in vision-language pre-training via contrastive learning have significantly improved performance across computer vision tasks. However, in the medical domain, obtaining multimodal data is often costly and challenging due…

Vision-Language models like CLIP have been widely adopted for various tasks due to their impressive zero-shot capabilities. However, CLIP is not suitable for extracting 3D geometric features as it was trained on only images and text by…

Unsupervised adaptation of CLIP-based vision-language models (VLMs) for fine-grained image classification requires sensitivity to microscopic local cues. While CLIP exhibits strong zero-shot transfer, its reliance on coarse global features…

Unsupervised 3D representation learning reduces the burden of labeling multimodal 3D data for fusion perception tasks. Among different pre-training paradigms, differentiable-rendering-based methods have shown most promise. However, existing…

Medical image analysis requires substantial labeled data for model training, yet expert annotation is expensive and time-consuming. Active learning (AL) addresses this challenge by strategically selecting the most informative samples for…

Recently, Contrastive Language-Image Pre-training (CLIP) has shown promising performance in domain-specific data (e.g., biology), and has attracted increasing research attention. Existing works generally focus on collecting extensive…