Related papers: 3D MRI Image Pretraining via Controllable 2D Slice…

The Segment Anything Model (SAM) has achieved a notable success in two-dimensional image segmentation in natural images. However, the substantial gap between medical and natural images hinders its direct application to medical image…

The requirement for expert annotations limits the effectiveness of deep learning for medical image analysis. Although 3D self-supervised methods like volume contrast learning (VoCo) are powerful and partially address the labeling scarcity…

Tissue manipulation is a frequently used fundamental subtask of any surgical procedures, and in some cases it may require the involvement of a surgeon's assistant. The complex dynamics of soft tissue as an unstructured environment is one of…

State-of-the-art deep learning-based registration methods employ three different learning strategies: supervised learning, which requires costly manual annotations, unsupervised learning, which heavily relies on hand-crafted similarity…

Surgical data science is a new research field that aims to observe all aspects of the patient treatment process in order to provide the right assistance at the right time. Due to the breakthrough successes of deep learning-based solutions…

In order to autonomously learn wide repertoires of complex skills, robots must be able to learn from their own autonomously collected data, without human supervision. One learning signal that is always available for autonomously collected…

State-of-the-art 3D object detectors are often trained on massive labeled datasets. However, annotating 3D bounding boxes remains prohibitively expensive and time-consuming, particularly for LiDAR. Instead, recent works demonstrate that…

3D Skeleton-based human action recognition has attracted increasing attention in recent years. Most of the existing work focuses on supervised learning which requires a large number of labeled action sequences that are often expensive and…

We present a new pre-training strategy called M$^{3}$3D ($\underline{M}$ulti-$\underline{M}$odal $\underline{M}$asked $\underline{3D}$) built based on Multi-modal masked autoencoders that can leverage 3D priors and learned cross-modal…

Reducing the quantity of annotations required for supervised training is vital when labels are scarce and costly. This reduction is particularly important for semantic segmentation tasks involving 3D datasets, which are often significantly…

The benefit of pretrained autoencoders for reinforcement learning in comparison to training on raw observations is already known [1]. In this paper, we address the generation of a compact and information-rich state representation. In…

We introduce an unsupervised feature learning approach that embeds 3D shape information into a single-view image representation. The main idea is a self-supervised training objective that, given only a single 2D image, requires all unseen…

Recent advancements in large-scale Vision Transformers have made significant strides in improving pre-trained models for medical image segmentation. However, these methods face a notable challenge in acquiring a substantial amount of…

In this work, we propose a novel straightforward method for medical volume and sequence segmentation with limited annotations. To avert laborious annotating, the recent success of self-supervised learning(SSL) motivates the pre-training on…

Self-supervised pre-training paradigms have been extensively explored in the field of skeleton-based action recognition. In particular, methods based on masked prediction have pushed the performance of pre-training to a new height. However,…

3D semantic segmentation plays a pivotal role in autonomous driving and road infrastructure analysis, yet state-of-the-art 3D models are prone to severe domain shift when deployed across different datasets. In this paper, we propose an…

We address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel self-supervised tasks using video data, the learned features are merely on a…

Motions are reflected in videos as the movement of pixels, and actions are essentially patterns of inconsistent motions between the foreground and the background. To well distinguish the actions, especially those with complicated…

A robot's ability to act is fundamentally constrained by what it can perceive. Many existing approaches to visual representation learning utilize general-purpose training criteria, e.g. image reconstruction, smoothness in latent space, or…

Due to the scarcity of labeled data, self-supervised learning (SSL) has gained much attention in 3D medical image segmentation, by extracting semantic representations from unlabeled data. Among SSL strategies, Masked image modeling (MIM)…