Related papers: An Improved Masking Strategy for Self-supervised M…
Magnetic resonance imaging (MRI) is indispensable for diagnosing and planning treatment in various medical conditions due to its ability to produce multi-series images that reveal different tissue characteristics. However, integrating these…
Unsupervised anomaly detection and segmentation methods train a model to learn the training distribution as `normal'. In the testing phase, they identify patterns that deviate from this normal distribution as `anomalies'. To learn the…
Thousands of people suffer from cranial injuries every year. They require personalized implants that need to be designed and manufactured before the reconstruction surgery. The manual design is expensive and time-consuming leading to…
Existing Masked Image Modeling methods apply fixed mask patterns to guide the self-supervised training. As those mask patterns resort to different criteria to depict image contents, sticking to a fixed pattern leads to a limited vision cues…
Deep learning techniques have gained considerable attention for their ability to accelerate MRI data acquisition while maintaining scan quality. In this work, we present a convolutional neural network (CNN) based framework for learning…
Self-supervised representation learning of Multivariate Time Series (MTS) is a challenging task and attracts increasing research interests in recent years. Many previous works focus on the pretext task of self-supervised learning and…
Deep learning has significantly advanced PET image re-construction, achieving remarkable improvements in image quality through direct training on sinogram or image data. Traditional methods often utilize masks for inpainting tasks, but…
Sensor-based human activity segmentation and recognition are two important and challenging problems in many real-world applications and they have drawn increasing attention from the deep learning community in recent years. Most of the…
Pre-training with random masked inputs has emerged as a novel trend in self-supervised training. However, supervised learning still faces a challenge in adopting masking augmentations, primarily due to unstable training. In this paper, we…
Traditional self-supervised learning requires CNNs using external pretext tasks (i.e., image- or video-based tasks) to encode high-level semantic visual representations. In this paper, we show that feature transformations within CNNs can…
As a successful approach to self-supervised learning, contrastive learning aims to learn invariant information shared among distortions of the input sample. While contrastive learning has yielded continuous advancements in sampling strategy…
Semantic segmentation is essential in computer vision for various applications, yet traditional approaches face significant challenges, including the high cost of annotation and extensive training for supervised learning. Additionally, due…
Masked autoencoding has achieved great success for self-supervised learning in the image and language domains. However, mask based pretraining has yet to show benefits for point cloud understanding, likely due to standard backbones like…
Inspired by the recent success of sequence modeling in RL and the use of masked language model for pre-training, we propose a masked model for pre-training in RL, RePreM (Representation Pre-training with Masked Model), which trains the…
Learning transferable representations from unlabeled time series is crucial for improving performance in data-scarce classification. Existing self-supervised methods often operate at the point level and rely on unidirectional encoding,…
Sensor-based human activity recognition is important in daily scenarios such as smart healthcare and homes due to its non-intrusive privacy and low cost advantages, but the problem of out-of-domain generalization caused by differences in…
The emergence of foundation models in neuroimaging is driven by the increasing availability of large-scale and heterogeneous brain imaging datasets. Recent advances in self-supervised learning, particularly reconstruction-based objectives,…
Recent works have correlated Masked Image Modeling (MIM) with consistency regularization in Unsupervised Domain Adaptation (UDA). However, they merely treat masking as a special form of deformation on the input images and neglect the…
Person re-identification (re-ID) is a challenging task in real-world. Besides the typical application in surveillance system, re-ID also has significant values to improve the recall rate of people identification in content video (TV or…
Because of the internal malfunction of satellite sensors and poor atmospheric conditions such as thick cloud, the acquired remote sensing data often suffer from missing information, i.e., the data usability is greatly reduced. In this…