Probabilistic Joint Image Segmentation and Labeling by Figure-Ground Composition

Ion, Adrian; Carreira, João; Sminchisescu, Cristian

doi:10.1007/s11263-013-0663-7

Cited by 32 publications

(37 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this Figure, label Table 3: Performance accuracy on VOC 2011 dataset using the proposed approach and state of the art fully supervised approaches [22], [6], [5] and [20]. The best results achieved by FS and WS approaches are highlighted in bold.…”

Section: Discussionmentioning

confidence: 99%

Weakly Supervised Graph Based Semantic Segmentation by Learning Communities of Image-Parts

Pourian

Karthikeyan

Manjunath

2015

2015 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Weakly Supervised Graph Based Semantic Segmentation by Learning Communities of Image-Parts

Pourian

Karthikeyan

Manjunath

2015

2015 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…Probabilistic methods have proven to be effective on 1D sequences with numerous applications such as information extraction in text, handwriting and voice recognition, or even 1D-signal segmentation. These methods have been adapted to 2D-signals through either Markov Random Field (MRF) [12,13] or 2D-CRF [14,15,9], but they both suffer from a time consuming and suboptimal decoding process such as HCF or ICM [16,17]. Indeed, one has to search for the best path among the huge number of possible paths in the observation trellis which dramatically increases with the signal and output size.…”

Section: Global Image Labeling Approachesmentioning

confidence: 99%

IODA: An input/output deep architecture for image labeling

Lerouge

Hérault

Chatelain

et al. 2015

Pattern Recognition

View full text Add to dashboard Cite

In this article, we propose a deep neural network (DNN) architecture called Input Output Deep Architecture (IODA) for solving the problem of image labeling. IODA directly links a whole image to a whole label map, assigning a label to each pixel using a unique neural network forward. Instead of designing a handcrafted a priori model on labels (such as an atlas in the medical domain), we propose to automatically learn the dependencies between labels. The originality of IODA is to transpose DNN pre-training input trick to outputs, in order to learn a high level representation of labels. It allows a fast image labeling inside a fully neural network framework, without the need of any preprocessing such as feature designing or output coding. In this article, IODA is applied on both a toy texture problem and a real-world medical image dataset, showing promising results. We provide an open source implementation of IODA. AbstractIn this article, we propose a deep neural network (DNN) architecture called Input Output Deep Architecture (IODA) for solving the problem of image labeling. IODA directly links a whole image to a whole label map, assigning a label to each pixel using a single neural network forward step. Instead of designing a handcrafted a priori model on labels (such as an atlas in the medical domain), we propose to automatically learn the dependencies between labels. The originality of IODA is to transpose DNN input pre-training trick to the output space, in order to learn a high level representation of labels. It allows a fast image labeling inside a fully neural network framework, without the need of any preprocessing such as feature designing or output coding.In this article, IODA is applied on both a toy texture problem and a realworld medical image dataset, showing promising results. We provide an open source implementation of IODA 12 .

show abstract

“…If fully-supervised training data is available, the most effective method is to train discriminative models that can be used to directly classify individual image regions. These local predictions are typically guided towards global consistency using prior knowledge such as local similarity [4,9,19], contextual geometric constraints [37], or agreement between multiple independent segmentations [1,16]. More recently, convolutional neural networks (CNNs) have been applied to region classification with great success [10,27].…”

Section: Transformation-invariant Representationsmentioning

confidence: 99%

Semantic Component Analysis

Murdock

Torre

2015

2015 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Unsupervised and weakly-supervised visual learning in large image collections are critical in order to avoid the time-consuming and error-prone process of manual labeling. Standard approaches rely on methods like multipleinstance learning or graphical models, which can be computationally intensive and sensitive to initialization. On the other hand, simpler component analysis or clustering methods usually cannot achieve meaningful invariances or semantic interpretability. To address the issues of previous work, we present a simple but effective method called Semantic Component Analysis (SCA), which provides a decomposition of images into semantic components.Unsupervised SCA decomposes additive image representations into spatially-meaningful visual components that naturally correspond to object categories. Using an overcomplete representation that allows for rich instance-level constraints and spatial priors, SCA gives improved results and more interpretable components in comparison to traditional matrix factorization techniques. If weakly-supervised information is available in the form of image-level tags, SCA factorizes a set of images into semantic groups of superpixels. We also provide qualitative connections to traditional methods for component analysis (e.g. Grassmann averages, PCA, and NMF). The effectiveness of our approach is validated through synthetic data and on the MSRC2 and Sift Flow datasets, demonstrating competitive results in unsupervised and weakly-supervised semantic segmentation.

show abstract

Probabilistic Joint Image Segmentation and Labeling by Figure-Ground Composition

Cited by 32 publications

References 25 publications

Weakly Supervised Graph Based Semantic Segmentation by Learning Communities of Image-Parts

Weakly Supervised Graph Based Semantic Segmentation by Learning Communities of Image-Parts

IODA: An input/output deep architecture for image labeling

Semantic Component Analysis

Contact Info

Product

Resources

About