相关论文: Uncertainty-based method for improving poorly labe…

Deep learning methods have achieved promising performance in many areas, but they are still struggling with noisy-labeled images during the training process. Considering that the annotation quality indispensably relies on great expertise,…

Despite the superior performance of Deep Learning (DL) on numerous segmentation tasks, the DL-based approaches are notoriously overconfident about their prediction with highly polarized label probability. This is often not desirable for…

Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are…

Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we…

Training neural networks using limited annotations is an important problem in the medical domain. Deep Neural Networks (DNNs) typically require large, annotated datasets to achieve acceptable performance which, in the medical domain, are…

Fluorescence microscopy images contain several channels, each indicating a marker staining the sample. Since many different marker combinations are utilized in practice, it has been challenging to apply deep learning based segmentation…

Semantic segmentation is the task of assigning a label to each pixel in the image.In recent years, deep convolutional neural networks have been driving advances in multiple tasks related to cognition. Although, DCNNs have resulted in…

Recent advances in deep learning algorithms have led to significant benefits for solving many medical image analysis problems. Training deep learning models commonly requires large datasets with expert-labeled annotations. However,…

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.…

Many successful methods developed for medical image analysis that are based on machine learning use supervised learning approaches, which often require large datasets annotated by experts to achieve high accuracy. However, medical data…

We present an approach to learn a dense pixel-wise labeling from image-level tags. Each image-level tag imposes constraints on the output labeling of a Convolutional Neural Network (CNN) classifier. We propose Constrained CNN (CCNN), a…

Recently, methods based on Convolutional Neural Networks (CNN) achieved impressive success in semantic segmentation tasks. However, challenges such as the class imbalance and the uncertainty in the pixel-labeling process are not completely…

Large annotated datasets are vital for training segmentation models, but pixel-level labeling is time-consuming, error-prone, and often requires scarce expert annotators, especially in medical imaging. In contrast, coarse annotations are…

Fine-grained annotations---e.g. dense image labels, image segmentation and text tagging---are useful in many ML applications but they are labor-intensive to generate. Moreover there are often systematic, structured errors in these…

Training a Convolutional Neural Network (CNN) for semantic segmentation typically requires to collect a large amount of accurate pixel-level annotations, a hard and expensive task. In contrast, simple image tags are easier to gather. With…

Semi-supervised segmentation tackles the scarcity of annotations by leveraging unlabeled data with a small amount of labeled data. A prominent way to utilize the unlabeled data is by consistency training which commonly uses a…

We propose a novel weakly-supervised semantic segmentation algorithm based on Deep Convolutional Neural Network (DCNN). Contrary to existing weakly-supervised approaches, our algorithm exploits auxiliary segmentation annotations available…

Deep neural network-based semantic segmentation generally requires large-scale cost extensive annotations for training to obtain better performance. To avoid pixel-wise segmentation annotations which are needed for most methods, recently…

Deep neural networks (DNNs) have achieved remarkable success in a variety of computer vision tasks, where massive labeled images are routinely required for model optimization. Yet, the data collected from the open world are unavoidably…

This paper proposes a new framework for semantic segmentation of objects in videos. We address the label inconsistency problem of deep convolutional neural networks (DCNNs) by exploiting the fact that videos have multiple frames; in a few…