相关论文: PCRLv2: A Unified Visual Information Preservation …

Self-supervised learning (SSL) has recently achieved promising performance for 3D medical image analysis tasks. Most current methods follow existing SSL paradigm originally designed for photographic or natural images, which cannot…

Self-supervised learning (SSL), which aims to learn meaningful prior representations from unlabeled data, has been proven effective for skeleton-based action understanding. Different from the image domain, skeleton data possesses sparser…

We present a new framework for self-supervised representation learning by formulating it as a ranking problem in an image retrieval context on a large number of random views (augmentations) obtained from images. Our work is based on two…

Vision transformers, with their ability to more efficiently model long-range context, have demonstrated impressive accuracy gains in several computer vision and medical image analysis tasks including segmentation. However, such methods need…

Reinforcement learning (RL) with verifiable rewards (RLVR) has demonstrated the great potential of enhancing the reasoning abilities in multimodal large language models (MLLMs). However, the reliance on language-centric priors and expensive…

Medical image labels are often organized by taxonomies (e.g., organ - tissue - subtype), yet standard self-supervised learning (SSL) ignores this structure. We present a hierarchy-preserving contrastive framework that makes the label tree a…

Self-supervised learning (SSL) has emerged as a promising paradigm in medical imaging, addressing the chronic challenge of limited labeled data in healthcare settings. While SSL has shown impressive results, existing studies in the medical…

Self Supervised learning (SSL) has demonstrated its effectiveness in feature learning from unlabeled data. Regarding this success, there have been some arguments on the role that mutual information plays within the SSL framework. Some works…

Self-supervised learning (SSL) has produced a diverse landscape of vision transformers (ViTs) whose pretrained representations support a wide range of downstream tasks. Towards a better understanding of these models, a body of work has…

Siamese-network-based self-supervised learning (SSL) suffers from slow convergence and instability in training. To alleviate this, we propose a framework to exploit intermediate self-supervisions in each stage of deep nets, called the…

In this work, we devote ourselves to the challenging task of Unsupervised Multi-view Representation Learning (UMRL), which requires learning a unified feature representation from multiple views in an unsupervised manner. Existing UMRL…

Semi-Supervised Learning (SSL) is important for reducing the annotation cost for medical image segmentation models. State-of-the-art SSL methods such as Mean Teacher, FixMatch and Cross Pseudo Supervision (CPS) are mainly based on…

Self-supervised learning (SSL) methods have achieved remarkable success in learning image representations allowing invariances in them - but therefore discarding transformation information that some computer vision tasks actually require.…

Deep learning technologies have already demonstrated a high potential to build diagnosis support systems from medical imaging data, such as Chest X-Ray images. However, the shortage of labeled data in the medical field represents one key…

Background: CT imaging is vital for lung cancer management, offering detailed visualization for AI-based prognosis. However, supervised learning SL models require large labeled datasets, limiting their real-world application in settings…

We propose a novel continual self-supervised learning (CSSL) framework for simultaneously learning diverse features from multi-window-obtained chest computed tomography (CT) images and ensuring data privacy. Achieving a robust and highly…

Liver tumor segmentation is essential for computer-aided diagnosis, surgical planning, and prognosis evaluation. However, obtaining and maintaining a large-scale dataset with dense annotations is challenging. Semi-Supervised Learning (SSL)…

Self-supervised vision-language pretraining from pure images and text with a contrastive loss is effective, but ignores fine-grained alignment due to a dual-stream architecture that aligns image and text representations only on a global…

Although supervised learning has been highly successful in improving the state-of-the-art in the domain of image-based computer vision in the past, the margin of improvement has diminished significantly in recent years, indicating that a…

Semi-supervised learning (SSL) aims to help reduce the cost of the manual labelling process by leveraging a substantial pool of unlabelled data alongside a limited set of labelled data during the training phase. Since pixel-level manual…