English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Affordances are the possibilities of actions the environment offers to theindividual. Ordinary objects (hammer, knife) usually have many affordances(grasping, pounding, cutting), and detecting these allow artificial agents tounderstand what are their possibilities in the environment, with obviousapplication in Robotics. Proposed benchmarks and state-of-the-art predictionmodels for supervised affordance segmentation are usually modifications ofpopular object segmentation models such as Mask R-CNN. We observe thattheoretically, these popular object segmentation methods should be sufficientfor detecting affordances masks. So we ask the question: is it necessary totailor new architectures to the problem of learning affordances? We show thatapplying the out-of-the-box Mask R-CNN to the problem of affordancessegmentation outperforms the current state-of-the-art. We conclude that theproblem of supervised affordance segmentation is included in the problem ofobject segmentation and argue that better benchmarks for affordance learningshould include action capacities.

Are standard Object Segmentation models sufficient for Learning Affordance Segmentation?