Related papers: AnyStar: Domain randomized universal star-convex 3…

Development of deep learning systems for biomedical segmentation often requires access to expert-driven, manually annotated datasets. If more than a single expert is involved in the annotation of the same images, then the inter-expert…

Interactive 3D point cloud segmentation enables efficient annotation of complex 3D scenes through user-guided prompts. However, current approaches are typically restricted in scope to a single domain (indoor or outdoor), and to a single…

Annotation cost is a bottleneck for collecting massive data in mammography, especially for training deep neural networks. In this paper, we study the use of heterogeneous levels of annotation granularity to improve predictive performances.…

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…

Instance segmentation for unlabeled imaging modalities is a challenging but essential task as collecting expert annotation can be expensive and time-consuming. Existing works segment a new modality by either deploying a pre-trained model…

Panoptic segmentation has recently unified semantic and instance segmentation, previously addressed separately, thus taking a step further towards creating more comprehensive and efficient perception systems. In this paper, we present…

Automatic semantic segmentation of magnetic resonance imaging (MRI) images using deep neural networks greatly assists in evaluating and planning treatments for various clinical applications. However, training these models is conditioned on…

A major impediment in rapidly deploying object detection models for instance detection is the lack of large annotated datasets. For example, finding a large labeled dataset containing instances in a particular kitchen is unlikely. Each new…

With the incredible results achieved from generative pre-trained transformers (GPT) and diffusion models, generative AI (GenAI) is envisioned to yield remarkable breakthroughs in various industrial and academic domains. In this paper, we…

The most common approaches to instance segmentation are complex and use two-stage networks with object proposals, conditional random-fields, template matching or recurrent neural networks. In this work we present TernausNetV2 - a simple…

Diffusion models are at the vanguard of generative AI research with renowned solutions such as ImageGen by Google Brain and DALL.E 3 by OpenAI. Nevertheless, the potential merits of diffusion models for communication engineering…

Accurate segmentation of critical anatomical structures is at the core of medical image analysis. The main bottleneck lies in gathering the requisite expert-labeled image annotations in a scalable manner. Methods that permit to produce…

Collecting image annotations remains a significant burden when deploying CNN in a specific applicative context. This is especially the case when the annotation consists in binary masks covering object instances. Our work proposes to…

Analyzing the geometric and semantic properties of 3D point clouds through the deep networks is still challenging due to the irregularity and sparsity of samplings of their geometric structures. This paper presents a new method to define…

Automatic instance segmentation is a problem that occurs in many biomedical applications. State-of-the-art approaches either perform semantic segmentation or refine object bounding boxes obtained from detection methods. Both suffer from…

Automated cellular instance segmentation is a process utilized for accelerating biological research for the past two decades, and recent advancements have produced higher quality results with less effort from the biologist. Most current…

Deep learning methods typically require vast amounts of training data to reach their full potential. While some publicly available datasets exists, domain specific data always needs to be collected and manually labeled, an expensive, time…

Instance segmentation has witnessed promising advancements through deep neural network-based algorithms. However, these models often exhibit incorrect predictions with unwarranted confidence levels. Consequently, evaluating prediction…

As segmentation labels are scarce, extensive researches have been conducted to train segmentation networks with domain adaptation, semi-supervised or self-supervised learning techniques to utilize abundant unlabeled dataset. However, these…

The generalization capability of unsupervised domain adaptation can mitigate the need for extensive pixel-level annotations to train semantic segmentation networks by training models on synthetic data as a source with computer-generated…