The remarkable performance of the Transformer architecture in natural language processing
has recently also triggered broad interest in Computer Vision. Among other merits …

Obtaining large pre-trained models that can be fine-tuned to new tasks with limited
annotated samples has remained an open challenge for medical imaging data. While pre …

In 3D medical image segmentation, data collection and annotation costs require significant
human efforts. Moreover, obtaining training data is challenging due to privacy constraints …

Diabetic retinopathy (DR) is a common complication of diabetes, which can lead to vision
loss. Early diagnosis is crucial to prevent the progression of DR. In recent years, deep …

Increasing the throughput of the Transformer architecture, a foundational component used in
numerous state-of-the-art models for vision and language tasks (eg, GPT, LLaVa), is an …

Harnessing the power of pre-training on large-scale datasets like ImageNet forms a
fundamental building block for the progress of representation learning-driven solutions in …

Diabetic Retinopathy (DR) is a leading cause of vision loss in the world, and early DR
detection is necessary to prevent vision loss and support an appropriate treatment. In this …

Abstract Vision-Language Pre-training (VLP) has shown the merits of analysing medical
images. It efficiently learns visual representations by leveraging supervisions in their …

In this work, we attempted to extend the thought and showcase a way forward for the Self-
supervised Learning (SSL) learning paradigm by combining contrastive learning, self …

The construction of 3D medical image datasets presents several issues, including requiring
significant financial costs in data collection and specialized expertise for annotation, as well …