Perceptually Inspired Layout-Aware Losses for Image Segmentation

10 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs (2016, background): “Similarly to Osokin & Kohli (2014), the complex dependence of the loss on the ground-truth labeling does not influence the complexity of the max oracle.”
Parametric Adversarial Divergences are Good Task Losses for Generative Modeling (2017, background): “In the context of image segmentation, Osokin & Kohli (2014) have compared various structured loss functions which induces different properties on the predicted mask.”
Context-Aware CNNs for Person Head Detection (2015, unknown): “Possible choices for h include the Hamming loss, the Hamming loss with penalties normalized by the frequency of classes, or higher-order losses making use of assumption that each ground-truth object is assigned to exactly one object candidate [26].”