Related papers: Extreme Point Supervised Instance Segmentation

Deep learning has achieved remarkable success in medicalimage segmentation, but it usually requires a large numberof images labeled with fine-grained segmentation masks, andthe annotation of these masks can be very expensive…

3D object detection is an important task in computer vision. Most existing methods require a large number of high-quality 3D annotations, which are expensive to collect. Especially for outdoor scenes, the problem becomes more severe due to…

Video instance segmentation requires detecting, segmenting, and tracking objects in videos, typically relying on costly video annotations. This paper introduces a method that eliminates video annotations by utilizing image datasets. The…

We propose a new and, arguably, a very simple reduction of instance segmentation to semantic segmentation. This reduction allows to train feed-forward non-recurrent deep instance segmentation systems in an end-to-end fashion using…

Pixel-wise segmentation is one of the most data and annotation hungry tasks in our field. Providing representative and accurate annotations is often mission-critical especially for challenging medical applications. In this paper, we propose…

We present a semi-supervised method for panoptic segmentation based on ConsInstancy regularisation, a novel strategy for semi-supervised learning. It leverages completely unlabelled data by enforcing consistency between predicted instance…

Dominated point cloud-based 3D object detectors in autonomous driving scenarios rely heavily on the huge amount of accurately labeled samples, however, 3D annotation in the point cloud is extremely tedious, expensive and time-consuming. To…

In this paper, we show that recent advances in self-supervised feature learning enable unsupervised object discovery and semantic segmentation with a performance that matches the state of the field on supervised semantic segmentation 10…

Learning dense point-wise semantics from unstructured 3D point clouds with fewer labels, although a realistic problem, has been under-explored in literature. While existing weakly supervised methods can effectively learn semantics with only…

Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques. Building on the successes of recent Transformer-based methods for object…

Instance segmentation requires a large number of training samples to achieve satisfactory performance and benefits from proper data augmentation. To enlarge the training set and increase the diversity, previous methods have investigated…

As a computer vision task, automatic object segmentation remains challenging in specialized image domains without massive labeled data, such as synthetic aperture sonar images, remote sensing, biomedical imaging, etc. In any domain,…

We present a bottom-up approach for the task of object instance segmentation using a single-shot model. The proposed model employs a fully convolutional network which is trained to predict class-wise segmentation masks as well as the…

In the past few years, we have seen great progress in perception algorithms, particular through the use of deep learning. However, most existing approaches focus on a few categories of interest, which represent only a small fraction of the…

In this paper, we present a semi supervised deep quick learning framework for instance detection and pixel-wise semantic segmentation of images in a dense clutter of items. The framework can quickly and incrementally learn novel items in an…

Object detection and semantic segmentation are both scene understanding tasks yet they differ in data structure and information level. Object detection requires box coordinates for object instances while semantic segmentation requires…

Training deep object detectors demands expensive bounding box annotation. Active learning (AL) is a promising technique to alleviate the annotation burden. Performing AL at box-level for object detection, i.e., selecting the most…

Methods for object detection and segmentation rely on large scale instance-level annotations for training, which are difficult and time-consuming to collect. Efforts to alleviate this look at varying degrees and quality of supervision.…

Instance Segmentation, which seeks to obtain both class and instance labels for each pixel in the input image, is a challenging task in computer vision. State-of-the-art algorithms often employ two separate stages, the first one generating…

Unsupervised panoptic segmentation aims to partition an image into semantically meaningful regions and distinct object instances without training on manually annotated data. In contrast to prior work on unsupervised panoptic scene…