Weakly Supervised Semantic Segmentation Using Constrained Dominant Sets

  title={Weakly Supervised Semantic Segmentation Using Constrained Dominant Sets},
  author={Sinem Aslan and Marcello Pelillo},
The availability of large-scale data sets is an essential prerequisite for deep learning based semantic segmentation schemes. Since obtaining pixel-level labels is extremely expensive, supervising deep semantic segmentation networks using low-cost weak annotations has been an attractive research problem in recent years. In this work, we explore the potential of Constrained Dominant Sets (CDS) for generating multi-labeled full mask predictions to train a fully convolutional network (FCN) for… 

Figures, Tables, and Topics from this paper

Constrained Dominant sets and Its applications in computer vision
New schemes which leverage a constrained clustering method to solve several computer vision tasks ranging from image retrieval, image segmentation and co-segmentation, to person re-identification are presented.


Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation
Expectation-Maximization (EM) methods for semantic image segmentation model training under weakly supervised and semi-supervised settings are developed and extensive experimental evaluation shows that the proposed techniques can learn models delivering competitive results on the challenging PASCAL VOC 2012 image segmentsation benchmark, while requiring significantly less annotation effort.
BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
  • Jifeng Dai, Kaiming He, Jian Sun
  • Computer Science
    2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
This paper proposes a method that achieves competitive accuracy but only requires easily obtained bounding box annotations, and yields state-of-the-art results on PASCAL VOC 2012 and PASCal-CONTEXT.
Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing
This paper proposes to train a semantic segmentation network starting from the discriminative regions and progressively increase the pixel-level supervision using by seeded region growing, and obtains the state-of-the-art performance.
Learning Random-Walk Label Propagation for Weakly-Supervised Semantic Segmentation
It is shown that by learning the label-propagator jointly with the segmentation predictor, the network is able to effectively learn semantic edges given no direct edge supervision, and that training a segmentation network in this way outperforms the naive approach.
Normalized Cut Loss for Weakly-Supervised CNN Segmentation
This work proposes a new principled loss function evaluating network output with criteria standard in "shallow" segmentation, e.g. normalized cut which evaluates only seeds where labels are known while normalized cut softly evaluates consistency of all pixels.
Simple Does It: Weakly Supervised Instance and Semantic Segmentation
This work proposes a new approach that does not require modification of the segmentation training procedure and shows that when carefully designing the input labels from given bounding boxes, even a single round of training is enough to improve over previously reported weakly supervised results.
On Regularized Losses for Weakly-supervised CNN Segmentation
This approach simplifies weakly-supervised training by avoiding extra MRF/CRF inference steps or layers explicitly generating full masks, while improving both the quality and efficiency of training.
ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
This paper proposes to use scribbles to annotate images, and develops an algorithm to train convolutional networks for semantic segmentation supervised by scribbles, which shows excellent results on the PASCALCONTEXT dataset thanks to extra inexpensive scribble annotations.
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF).
What's the Point: Semantic Segmentation with Point Supervision
This work takes a natural step from image-level annotation towards stronger supervision: it asks annotators to point to an object if one exists, and incorporates this point supervision along with a novel objectness potential in the training loss function of a CNN model.