Related papers: The Missing Piece: A Case for Pre-Training in 3D M…

Multi-organ segmentation is one of most successful applications of deep learning in medical image analysis. Deep convolutional neural nets (CNNs) have shown great promise in achieving clinically applicable image segmentation performance on…

Deep convolutional neural networks (CNNs) are state-of-the-art for semantic image segmentation, but typically require many labeled training samples. Obtaining 3D segmentations of medical images for supervised training is difficult and labor…

Annotating medical imaging datasets is costly, so fine-tuning (or transfer learning) is the most effective method for digital pathology vision applications such as disease classification and semantic segmentation. However, due to texture…

Recent co-part segmentation methods mostly operate in a supervised learning setting, which requires a large amount of annotated data for training. To overcome this limitation, we propose a self-supervised deep learning method for co-part…

A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge. This paper proposes a novel approach to point-cloud…

Volumetric medical segmentation is a critical component of 3D medical image analysis that delineates different semantic regions. Deep neural networks have significantly improved volumetric medical segmentation, but they generally require…

The performance of a trained object detection neural network depends a lot on the image quality. Generally, images are pre-processed before feeding them into the neural network and domain knowledge about the image dataset is used to choose…

This paper proposes a novel training model based on shape and appearance features for object segmentation in images and videos. Whereas most such models rely on two-dimensional appearance templates or a finite set of descriptors, our…

While self-supervised pretraining has proven beneficial for many computer vision tasks, it requires expensive and lengthy computation, large amounts of data, and is sensitive to data augmentation. Prior work demonstrates that models…

The field of self-supervised learning (SSL) for 3D medical images lacks consistency and standardization. While many methods have been developed, it is impossible to identify the current state-of-the-art, due to i) varying and small…

One of the largest problems in medical image processing is the lack of annotated data. Labeling medical images often requires highly trained experts and can be a time-consuming process. In this paper, we evaluate a method of reducing the…

Self-supervised pre-training for 3D vision has drawn increasing research interest in recent years. In order to learn informative representations, a lot of previous works exploit invariances of 3D features, e.g., perspective-invariance…

Object detection is a fundamental task for robots to operate in unstructured environments. Today, there are several deep learning algorithms that solve this task with remarkable performance. Unfortunately, training such systems requires…

Current fine-grained classification approaches often rely on a robust localization of object parts to extract localized feature representations suitable for discrimination. However, part localization is a challenging task due to the large…

With the rapid development and wide application of computer, camera device, network and hardware technology, 3D object (or model) retrieval has attracted widespread attention and it has become a hot research topic in the computer vision…

In clinical practice, 2D magnetic resonance (MR) sequences are widely adopted. While individual 2D slices can be stacked to form a 3D volume, the relatively large slice spacing can pose challenges for both image visualization and subsequent…

Molecular property prediction is one of the fastest-growing applications of deep learning with critical real-world impacts. Including 3D molecular structure as input to learned models improves their performance for many molecular tasks.…

The segmentation of medical images is important for the improvement and creation of healthcare systems, particularly for early disease detection and treatment planning. In recent years, the use of convolutional neural networks (CNNs) and…

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…

While the majority of today's object class models provide only 2D bounding boxes, far richer output hypotheses are desirable including viewpoint, fine-grained category, and 3D geometry estimate. However, models trained to provide richer…