相关论文: Revisiting pre-trained remote sensing model benchm…

Foundation models have advanced machine learning across various modalities, including images. Recently multiple teams trained foundation models specialized for remote sensing applications. This line of research is motivated by the distinct…

The growing demand for accurate and equitable AI models in digital dermatology faces a significant challenge: the lack of diverse, high-quality labeled data. In this work, we investigate the potential of domain-specific foundation models…

We evaluate the effectiveness of semi-supervised learning (SSL) on a realistic benchmark where data exhibits considerable class imbalance and contains images from novel classes. Our benchmark consists of two fine-grained classification…

In recent years Convolutional neural networks (CNN) have made significant progress in computer vision. These advancements have been applied to other areas, such as remote sensing and have shown satisfactory results. However, the lack of…

Machine learning methods for satellite data have a range of societally relevant applications, but labels used to train models can be difficult or impossible to acquire. Self-supervision is a natural solution in settings with limited labeled…

Self-supervised learning (SSL) for RGB images has achieved significant success, yet there is still limited research on SSL for infrared images, primarily due to three prominent challenges: 1) the lack of a suitable large-scale infrared…

Currently, under supervised learning, a model pretrained by a large-scale nature scene dataset and then fine-tuned on a few specific task labeling data is the paradigm that has dominated the knowledge transfer learning. It has reached the…

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…

We investigate the role of self-supervised learning (SSL) in the context of few-shot learning. Although recent research has shown the benefits of SSL on large unlabeled datasets, its utility on small datasets is relatively unexplored. We…

Recently, the self-supervised pre-training paradigm has shown great potential in leveraging large-scale unlabeled data to improve downstream task performance. However, increasing the scale of unlabeled pre-training data in real-world…

Linear probing (LP) (and $k$-NN) on the upstream dataset with labels (e.g., ImageNet) and transfer learning (TL) to various downstream datasets are commonly employed to evaluate the quality of visual representations learned via…

Models initialized from self-supervised pretraining may suffer from poor alignment with downstream tasks, reducing the extent to which subsequent fine-tuning can adapt pretrained features toward downstream objectives. To mitigate this, we…

Semi-supervised Learning (SSL) has witnessed great success owing to the impressive performances brought by various methods based on pseudo labeling and consistency regularization. However, we argue that existing methods might fail to…

Synthetic-to-real transfer learning is a framework in which a synthetically generated dataset is used to pre-train a model to improve its performance on real vision tasks. The most significant advantage of using synthetic images is that the…

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) has emerged as a promising paradigm for addressing the annotation bottleneck in medical imaging by learning representations from unlabeled data. However, its effectiveness depends heavily on the design of the…

Self-supervised learning (SSL) applied to natural images has demonstrated a remarkable ability to learn meaningful, low-dimension representations without labels, resulting in models that are adaptable to many different tasks. Until now,…

In medical image segmentation tasks, the scarcity of labeled training data poses a significant challenge when training deep neural networks. When using U-Net-style architectures, it is common practice to address this problem by pretraining…

Deep neural networks trained end-to-end to map a measurement of a (noisy) image to a clean image perform excellent for a variety of linear inverse problems. Current methods are only trained on a few hundreds or thousands of images as…

Although well-known large-scale datasets, such as ImageNet, have driven image understanding forward, most of these datasets require extensive manual annotation and are thus not easily scalable. This limits the advancement of image…