Related papers: Noisy Annotations in Semantic Segmentation

Two of the most common tasks in medical imaging are classification and segmentation. Either task requires labeled data annotated by experts, which is scarce and expensive to collect. Annotating data for segmentation is generally considered…

Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the…

Instance segmentation is a fundamental research in computer vision, especially in autonomous driving. However, manual mask annotation for instance segmentation is quite time-consuming and costly. To address this problem, some prior works…

We address the problem of weakly-supervised semantic segmentation (WSSS) using bounding box annotations. Although object bounding boxes are good indicators to segment corresponding objects, they do not specify object boundaries, making it…

Supervised learning depends on annotated examples, which are taken to be the \emph{ground truth}. But these labels often come from noisy crowdsourcing platforms, like Amazon Mechanical Turk. Practitioners typically collect multiple labels…

Deep ConvNets have shown great performance for single-label image classification (e.g. ImageNet), but it is necessary to move beyond the single-label classification task because pictures of everyday life are inherently multi-label.…

Existing research on learning with noisy labels mainly focuses on synthetic label noise. Synthetic noise, though has clean structures which greatly enabled statistical analyses, often fails to model real-world noise patterns. The recent…

Annotating new datasets for machine learning tasks is tedious, time-consuming, and costly. For segmentation applications, the burden is particularly high as manual delineations of relevant image content are often extremely expensive or can…

In recent decades, the vision community has witnessed remarkable progress in visual recognition, partially owing to advancements in dataset benchmarks. Notably, the established COCO benchmark has propelled the development of modern…

Convolutional neural networks (CNNs) have gained increasing popularity and versatility in recent decades, finding applications in diverse domains. These remarkable achievements are greatly attributed to the support of extensive datasets…

Semantic image segmentation is one of the most important tasks in medical image analysis. Most state-of-the-art deep learning methods require a large number of accurately annotated examples for model training. However, accurate annotation…

Instance segmentation methods require large datasets with expensive and thus limited instance-level mask labels. Partially supervised instance segmentation aims to improve mask prediction with limited mask labels by utilizing the more…

In real-world scenarios, collected and annotated data often exhibit the characteristics of multiple classes and long-tailed distribution. Additionally, label noise is inevitable in large-scale annotations and hinders the applications of…

Deep neural networks have achieved remarkable success in a wide variety of natural image and medical image computing tasks. However, these achievements indispensably rely on accurately annotated training data. If encountering some…

High annotation costs are a major bottleneck for the training of semantic segmentation systems. Therefore, methods working with less annotation effort are of special interest. This paper studies the problem of semi-supervised semantic…

Embodied intelligence relies on accurately segmenting objects actively involved in interactions. Action-based video object segmentation addresses this by linking segmentation with action semantics, but it depends on large-scale annotations…

Nuclei segmentation is a fundamental task in histopathology image analysis. Typically, such segmentation tasks require significant effort to manually generate accurate pixel-wise annotations for fully supervised training. To alleviate such…

The design of new methods and models when only weakly-labeled data are available is of paramount importance in order to reduce the costs of manual annotation and the considerable human effort associated with it. In this work, we address…

Learning from noisy labels (LNL) is a challenge that arises in many real-world scenarios where collected training data can contain incorrect or corrupted labels. Most existing solutions identify noisy labels and adopt active learning to…

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…