Learning to segment under various forms of weak supervision

Xu, Jia; Schwing, Alexander G.; Urtasun, Raquel

doi:10.1109/cvpr.2015.7299002

Cited by 176 publications

(165 citation statements)

References 29 publications

Supporting

Mentioning

165

Contrasting

Order By: Relevance

“…However, without explicitly modelling the label noise and solving it as a denoising problem, their performance is much weaker than that of ours as demonstrated in our experiments (see Section 5). Another existing work that is worth mentioning here is that of Xu et al [18]. Formulating the WSSS problem as a large-margin clustering method, this work is related to ours in that both methods iteratively estimate the superpixel labels and update superpixel appearance models 1 .…”

Section: Related Workmentioning

confidence: 95%

“…Existing weakly supervised semantic segmentation (WSSS) methods employ a variety of models including latent topic model [9], conditional random field (CRF) [17], [19], linear SVM [18], label propagation [13], multiinstance learning [10], [11], clustering [14], and sparse reconstruction [15]. They also differ in whether superpixelbased object appearance is explicitly modelled and whether they operate under an inductive or transductive setting, or both.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Learning from Weak and Noisy Labels for Semantic Segmentation

Xiang

et al. 2017

IEEE Trans. Pattern Anal. Mach. Intell.

113

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 95%

Section: Related Workmentioning

confidence: 99%

Learning from Weak and Noisy Labels for Semantic Segmentation

Xiang

et al. 2017

IEEE Trans. Pattern Anal. Mach. Intell.

113

View full text Add to dashboard Cite

“…Without additional priors only poor results are obtained. Using superpixels to inform about the object shape helps [33,47] and so does using priors on the object size [31]. [18] carefully uses CRFs to propagate the seeds across the image during training, while [36] exploits segment proposals for this.…”

Section: ( §4)mentioning

confidence: 99%

“…The weakly supervised learning problem can be seen as a specific instance of learning from constraints [38,47]. Instead of explicitly supervising the output, the available labels provide a constraint on the desired output.…”

Section: Introductionmentioning

confidence: 99%

Exploiting Saliency for Object Segmentation from Image Level Labels

Benenson

Khoreva

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

183

View full text Add to dashboard Cite

There have been remarkable improvements in the semantic labelling task in the recent years. However, the state of the art methods rely on large-scale pixel-level annotations. This paper studies the problem of training a pixel-wise semantic labeller network from image-level annotations of the present object classes. Recently, it has been shown that high quality seeds indicating discriminative object regions can be obtained from image-level labels. Without additional information, obtaining the full extent of the object is an inherently ill-posed problem due to co-occurrences. We propose using a saliency model as additional information and hereby exploit prior knowledge on the object extent and image statistics. We show how to combine both information sources in order to recover 80% of the fully supervised performance -which is the new state of the art in weakly supervised training for pixel-wise semantic labelling. The code is available at https://goo.gl/KygSeb.

show abstract

“…Some state-of-the-art methods [13] rely on dense pixel-wise correspondences, which is infeasible to apply to a large dataset of 3D medical images. In an attempt to overcome such issues, other methods advocate using superpixels in an image as a building block in unsupervised and weakly supervised segmentation [14,18,7], where feature descriptors are typically computed on a pixel-level and then aggregated within superpixels; however, descriptor choice is non-trivial and can still be computationally costly for 3D images depending on the type of features.…”

Section: Introductionmentioning

confidence: 99%

Joint Supervoxel Classification Forest for Weakly-Supervised Organ Segmentation

Kanavati

Misawa

Fujiwara

et al. 2017

Machine Learning in Medical Imaging

View full text Add to dashboard Cite

Abstract. This article presents an efficient method for weakly-supervised organ segmentation. It consists in over-segmenting the images into objectlike supervoxels. A single joint forest classifier is then trained on all the images, where (a) the supervoxel indices are used as labels for the voxels, (b) a joint node optimisation is done using training samples from all the images, and (c) in each leaf node, a distinct posterior distribution is stored per image. The result is a forest with a shared structure that efficiently encodes all the images in the dataset. The forest can be applied once on a given source image to obtain supervoxel label predictions for its voxels from all the other target images in the dataset by simply looking up the target's distribution in the leaf nodes. The output is then regularised using majority voting within the boundaries of the source's supervoxels. This yields sparse correspondences on an over-segmentation-based level in an unsupervised, efficient, and robust manner. Weak annotations can then be propagated to other images, extending the labelled set and allowing an organ label classification forest to be trained. We demonstrate the effectiveness of our approach on a dataset of 150 abdominal CT images where, starting from a small set of 10 images with scribbles, we perform weakly-supervised image segmentation of the kidneys, liver and spleen. Promising results are obtained.

show abstract

Learning to segment under various forms of weak supervision

Cited by 176 publications

References 29 publications

Learning from Weak and Noisy Labels for Semantic Segmentation

Learning from Weak and Noisy Labels for Semantic Segmentation

Exploiting Saliency for Object Segmentation from Image Level Labels

Joint Supervoxel Classification Forest for Weakly-Supervised Organ Segmentation

Contact Info

Product

Resources

About