Holistic, Instance-level Human Parsing

Qizhu Li, Anurag Arnab and Philip Torr

Abstract

Object parsing – the task of decomposing an object into its semantic parts – has traditionally been formulated as a category-level segmentation problem. Consequently, when there are multiple objects in an image, current methods cannot count the number of objects in the scene, nor can they determine which part belongs to which object. We address this problem by segmenting the parts of objects at an instance-level, such that each pixel in the image is assigned a part label, as well as the identity of the object it belongs to. Moreover, we show how this approach benefits us in obtaining segmentations at coarser granularities as well. Our proposed network is trained end-to-end given detections, and begins with a category-level segmentation module. Thereafter, a differentiable Conditional Random Field, defined over a variable number of instances for every input image, reasons about the identity of each part by associating it with a human detection.

Session

Posters

Files

Paper (PDF)
Supplementary (PDF)

DOI

10.5244/C.31.25
https://dx.doi.org/10.5244/C.31.25

Citation

Bibtex

            @inproceedings{BMVC2017_25,
                title={Holistic, Instance-level Human Parsing},
                author={Qizhu Li, Anurag Arnab and Philip Torr},
                year={2017},
                month={September},
                pages={25.1-25.13},
                articleno={25},
                numpages={13},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.25},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.25}
            }