What's the point: Semantic segmentation with point supervision
The semantic image segmentation task presents a trade-off between test time accuracy and
training time annotation cost. Detailed per-pixel annotations enable training accurate …
training time annotation cost. Detailed per-pixel annotations enable training accurate …
Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation
G Papandreou, LC Chen… - Proceedings of the …, 2015 - openaccess.thecvf.com
Deep convolutional neural networks (DCNNs) trained on a large number of images with
strong pixel-level annotations have recently significantly pushed the state-of-art in semantic …
strong pixel-level annotations have recently significantly pushed the state-of-art in semantic …
Seed, expand and constrain: Three principles for weakly-supervised image segmentation
A Kolesnikov, CH Lampert - Computer Vision–ECCV 2016: 14th European …, 2016 - Springer
We introduce a new loss function for the weakly-supervised training of semantic image
segmentation models based on three guiding principles: to seed with weak localization …
segmentation models based on three guiding principles: to seed with weak localization …
Stc: A simple to complex framework for weakly-supervised semantic segmentation
Recently, significant improvement has been made on semantic object segmentation due to
the development of deep convolutional neural networks (DCNNs). Training such a DCNN …
the development of deep convolutional neural networks (DCNNs). Training such a DCNN …
Constrained-CNN losses for weakly supervised segmentation
Weakly-supervised learning based on, eg, partially labelled images or image-tags, is
currently attracting significant attention in CNN segmentation as it can mitigate the need for …
currently attracting significant attention in CNN segmentation as it can mitigate the need for …
Prior-aware neural network for partially-supervised multi-organ segmentation
Accurate multi-organ abdominal CT segmentation is essential to many clinical applications
such as computer-aided intervention. As data annotation requires massive human labor …
such as computer-aided intervention. As data annotation requires massive human labor …
Annotating object instances with a polygon-rnn
In this paper, we propose an approach for semi-automatic annotation of object instances.
While most current methods treat object segmentation as a pixel-labeling problem, we here …
While most current methods treat object segmentation as a pixel-labeling problem, we here …
Not all unlabeled data are equal: Learning to weight data in semi-supervised learning
Existing semi-supervised learning (SSL) algorithms use a single weight to balance the loss
of labeled and unlabeled examples, ie, all unlabeled examples are equally weighted. But …
of labeled and unlabeled examples, ie, all unlabeled examples are equally weighted. But …
Histosegnet: Semantic segmentation of histological tissue type in whole slide images
L Chan, MS Hosseini, C Rowsell… - Proceedings of the …, 2019 - openaccess.thecvf.com
In digital pathology, tissue slides are scanned into Whole Slide Images (WSI) and
pathologists first screen for diagnostically-relevant Regions of Interest (ROIs) before …
pathologists first screen for diagnostically-relevant Regions of Interest (ROIs) before …
Learning deep structured models
Many problems in real-world applications involve predicting several random variables that
are statistically related. Markov random fields (MRFs) are a great mathematical tool to …
are statistically related. Markov random fields (MRFs) are a great mathematical tool to …