One-shot Texture Segmentation

By Ivan Ustyuzhaninov, Claudio Michaelis, Wieland Brendel, Matthias Bethge. 2018

18 citations recorded by the source corpus.

We introduce one-shot texture segmentation: the task of segmenting an input image containing multiple textures given a patch of a reference texture. This task is designed to turn the problem of texture-based perceptual grouping into an objective benchmark. We show that it is straight-forward to generate large synthetic data sets for this task from a relatively small number of natural textures. In particular, this task can be cast as a self-supervised problem thereby alleviating the need for massive amounts of manually annotated data necessary for traditional segmentation tasks. In this paper we introduce and study two concrete data sets: a dense collage of textures (CollTex) and a cluttered texturized Omniglot data set. We show that a baseline model trained on these synthesized data is able to generalize to natural images and videos without further fine-tuning, suggesting that the learned image representations are useful for higher-level vision tasks.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness (2018, background): “Our hypothesis might also explain why an image segmentation model trained on a database of synthetic texture images transfers to natural images and videos (Ustyuzhaninov et al., 2018).”
One-Shot Instance Segmentation (2018, background): “Closely related to our work is one-shot semantic segmentation of images using either an object instance as reference [78, 65, 20, 50] or a texture [83].”