Transferring dense pose to proximal animal classes
Recent contributions have demonstrated that it is possible to recognize the pose of humans densely and accurately given a large dataset of poses annotated in detail. In principle, the same approach could be extended to any animal class, but the effort required for collecting new annotations for each...
Main Authors: | , , , , |
---|---|
Format: | Conference item |
Language: | English |
Published: |
IEEE
2020
|
_version_ | 1797094975129780224 |
---|---|
author | Sanakoyeu, A Khalidov, V McCarthy, MS Vedaldi, A Neverova, N |
author_facet | Sanakoyeu, A Khalidov, V McCarthy, MS Vedaldi, A Neverova, N |
author_sort | Sanakoyeu, A |
collection | OXFORD |
description | Recent contributions have demonstrated that it is possible to recognize the pose of humans densely and accurately given a large dataset of poses annotated in detail. In principle, the same approach could be extended to any animal class, but the effort required for collecting new annotations for each case makes this strategy impractical, despite important applications in natural conservation, science and business. We show that, at least for proximal animal classes such as chimpanzees, it is possible to transfer the knowledge existing in dense pose recognition for humans, as well as in more general object detectors and segmenters, to the problem of dense pose recognition in other classes. We do this by (1) establishing a DensePose model for the new animal which is also geometrically aligned to humans (2) introducing a multi-head R-CNN architecture that facilitates transfer of multiple recognition tasks between classes, (3) finding which combination of known classes can be transferred most effectively to the new animal and (4) using self-calibrated uncertainty heads to generate pseudo-labels graded by quality for training a model for this class. We also introduce two benchmark datasets labelled in the manner of DensePose for the class chimpanzee and use them to evaluate our approach, showing excellent transfer learning performance. |
first_indexed | 2024-03-07T04:21:23Z |
format | Conference item |
id | oxford-uuid:cb21b976-2341-4228-8b31-e4c1276f5f26 |
institution | University of Oxford |
language | English |
last_indexed | 2024-03-07T04:21:23Z |
publishDate | 2020 |
publisher | IEEE |
record_format | dspace |
spelling | oxford-uuid:cb21b976-2341-4228-8b31-e4c1276f5f262022-03-27T07:12:43ZTransferring dense pose to proximal animal classesConference itemhttp://purl.org/coar/resource_type/c_5794uuid:cb21b976-2341-4228-8b31-e4c1276f5f26EnglishSymplectic ElementsIEEE2020Sanakoyeu, AKhalidov, VMcCarthy, MSVedaldi, ANeverova, NRecent contributions have demonstrated that it is possible to recognize the pose of humans densely and accurately given a large dataset of poses annotated in detail. In principle, the same approach could be extended to any animal class, but the effort required for collecting new annotations for each case makes this strategy impractical, despite important applications in natural conservation, science and business. We show that, at least for proximal animal classes such as chimpanzees, it is possible to transfer the knowledge existing in dense pose recognition for humans, as well as in more general object detectors and segmenters, to the problem of dense pose recognition in other classes. We do this by (1) establishing a DensePose model for the new animal which is also geometrically aligned to humans (2) introducing a multi-head R-CNN architecture that facilitates transfer of multiple recognition tasks between classes, (3) finding which combination of known classes can be transferred most effectively to the new animal and (4) using self-calibrated uncertainty heads to generate pseudo-labels graded by quality for training a model for this class. We also introduce two benchmark datasets labelled in the manner of DensePose for the class chimpanzee and use them to evaluate our approach, showing excellent transfer learning performance. |
spellingShingle | Sanakoyeu, A Khalidov, V McCarthy, MS Vedaldi, A Neverova, N Transferring dense pose to proximal animal classes |
title | Transferring dense pose to proximal animal classes |
title_full | Transferring dense pose to proximal animal classes |
title_fullStr | Transferring dense pose to proximal animal classes |
title_full_unstemmed | Transferring dense pose to proximal animal classes |
title_short | Transferring dense pose to proximal animal classes |
title_sort | transferring dense pose to proximal animal classes |
work_keys_str_mv | AT sanakoyeua transferringdenseposetoproximalanimalclasses AT khalidovv transferringdenseposetoproximalanimalclasses AT mccarthyms transferringdenseposetoproximalanimalclasses AT vedaldia transferringdenseposetoproximalanimalclasses AT neverovan transferringdenseposetoproximalanimalclasses |