Related papers: MixPolyp: Integrating Mask, Box and Scribble Super…

The success of medical image segmentation usually requires a large number of high-quality labels. But since the labeling process is usually affected by the raters' varying skill levels and characteristics, the estimated masks provided by…

3D instance segmentation is crucial for understanding complex 3D environments, yet fully supervised methods require dense point-level annotations, resulting in substantial annotation costs and labor overhead. To mitigate this, box-level…

This paper introduces a novel approach to learning instance segmentation using extreme points, i.e., the topmost, leftmost, bottommost, and rightmost points, of each object. These points are readily available in the modern bounding box…

Box-supervised polyp segmentation attracts increasing attention for its cost-effective potential. Existing solutions often rely on learning-free methods or pretrained models to laboriously generate pseudo masks, triggering Dice constraint…

Early detection of colorectal polyps is of utmost importance for their treatment and for colorectal cancer prevention. Computer vision techniques have the potential to aid professionals in the diagnosis stage, where colonoscopies are…

In clinical medicine, precise image segmentation can provide substantial support to clinicians. However, obtaining high-quality segmentation typically demands extensive pixel-level annotations, which are labor-intensive and expensive.…

Scribble-based weakly supervised segmentation methods have shown promising results in medical image segmentation, significantly reducing annotation costs. However, existing approaches often rely on auxiliary tasks to enforce semantic…

Curating a large set of fully annotated training data can be costly, especially for the tasks of medical image segmentation. Scribble, a weaker form of annotation, is more obtainable in practice, but training segmentation models from…

Most state-of-the-art instance segmentation methods have to be trained on densely annotated images. While difficult in general, this requirement is especially daunting for biomedical images, where domain expertise is often required for…

Box-supervised instance segmentation has gained much attention as it requires only simple box annotations instead of costly mask or polygon annotations. However, existing box-supervised instance segmentation models mainly focus on…

Mixup refers to interpolation-based data augmentation, originally motivated as a way to go beyond empirical risk minimization (ERM). Its extensions mostly focus on the definition of interpolation and the space (input or feature) where it…

Eye gaze that reveals human observational patterns has increasingly been incorporated into solutions for vision tasks. Despite recent explorations on leveraging gaze to aid deep networks, few studies exploit gaze as an efficient annotation…

We propose an embarrassingly simple point annotation scheme to collect weak supervision for instance segmentation. In addition to bounding boxes, we collect binary labels for a set of points uniformly sampled inside each bounding box. We…

Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks. Such pixel-accurate supervision demands expensive labeling effort and limits the…

Accurate segmentation of polyps and skin lesions is essential for diagnosing colorectal and skin cancers. While various segmentation methods for polyps and skin lesions using fully supervised deep learning techniques have been developed,…

In this paper, we propose a new approach to applying point-level annotations for weakly-supervised panoptic segmentation. Instead of the dense pixel-level labels used by fully supervised methods, point-level labels only provide a single…

Deep-learning methods have recently started being employed for addressing surface-defect detection problems in industrial quality control. However, with a large amount of data needed for learning, often requiring high-precision labels, many…

Current methods for 3D semantic segmentation propose training models with limited annotations to address the difficulty of annotating large, irregular, and unordered 3D point cloud data. They usually focus on the 3D domain only, without…

3D object detection is essential for autonomous driving and robotic perception, yet its reliance on large-scale manually annotated data limits scalability and adaptability. To reduce annotation dependency, unsupervised and…

Scribble-based weakly supervised semantic segmentation leverages only a few annotated pixels as labels to train a segmentation model, presenting significant potential for reducing the human labor involved in the annotation process. This…