Exploring and Exploiting Diversity for Image Segmentation

09/05/2017
by   Payman Yadollahpour, et al.
0

Semantic image segmentation is an important computer vision task that is difficult because it consists of both recognition and segmentation. The task is often cast as a structured output problem on an exponentially large output-space, which is typically modeled by a discrete probabilistic model. The best segmentation is found by inferring the Maximum a-Posteriori (MAP) solution over the output distribution defined by the model. Due to limitations in optimization, the model cannot be arbitrarily complex. This leads to a trade-off: devise a more accurate model that incorporates rich high-order interactions between image elements at the cost of inaccurate and possibly intractable optimization OR leverage a tractable model which produces less accurate MAP solutions but may contain high quality solutions as other modes of its output distribution. This thesis investigates the latter and presents a two stage approach to semantic segmentation. In the first stage a tractable segmentation model outputs a set of high probability segmentations from the underlying distribution that are not just minor perturbations of each other. Critically the output of this stage is a diverse set of plausible solutions and not just a single one. In the second stage, a discriminatively trained re-ranking model selects the best segmentation from this set. The re-ranking stage can use much more complex features than what could be tractably used in the segmentation model, allowing a better exploration of the solution space than simply returning the MAP solution. The formulation is agnostic to the underlying segmentation model (e.g. CRF, CNN, etc.) and optimization algorithm, which makes it applicable to a wide range of models and inference methods. Evaluation of the approach on a number of semantic image segmentation benchmark datasets highlight its superiority over inferring the MAP solution.

READ FULL TEXT

page 34

page 37

research
08/24/2019

Generator evaluator-selector net: a modular approach for panoptic segmentation

In machine learning and other fields, suggesting a good solution to a pr...
research
12/01/2021

SegDiff: Image Segmentation with Diffusion Probabilistic Models

Diffusion Probabilistic Methods are employed for state-of-the-art image ...
research
03/11/2022

Hyperbolic Image Segmentation

For image segmentation, the current standard is to perform pixel-level o...
research
09/20/2018

Recent progress in semantic image segmentation

Semantic image segmentation, which becomes one of the key applications i...
research
12/14/2014

Combining the Best of Graphical Models and ConvNets for Semantic Segmentation

We present a two-module approach to semantic segmentation that incorpora...
research
12/17/2019

PointRend: Image Segmentation as Rendering

We present a new method for efficient high-quality image segmentation of...
research
05/09/2018

Facade Segmentation in the Wild

Urban facade segmentation from automatically acquired imagery, in contra...

Please sign up or login with your details

Forgot password? Click here to reset