Adversarial Learning for 3D Matching

Wei Xing, Brian Ziebart
Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI), PMLR 124:869-878, 2020.

Abstract

Structured prediction of objects in spaces that are inherently difficult to search or compactly characterize is a particularly challenging task. For example, though bipartite matchings in two dimensions can be tractably optimized and learned, the higher-dimensional generalization—3D matchings—are NP-hard to optimally obtain and the set of potential solutions cannot be compactly characterized. Though approximation is therefore necessary, prevalent structured prediction methods inherit the weaknesses they possess in the two-dimensional setting either suffering from inconsistency or intractability—even when the approximations are sufficient. In this paper, we explore extending an adversarial approach to learning bipartite matchings that avoids these weaknesses to the three dimensional setting. We assess the benefits compared to margin-based methods on a three-frame tracking problem.

Cite this Paper


BibTeX
@InProceedings{pmlr-v124-xing20a, title = {Adversarial Learning for 3D Matching}, author = {Xing, Wei and Ziebart, Brian}, booktitle = {Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI)}, pages = {869--878}, year = {2020}, editor = {Jonas Peters and David Sontag}, volume = {124}, series = {Proceedings of Machine Learning Research}, month = {03--06 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v124/xing20a/xing20a.pdf}, url = { http://proceedings.mlr.press/v124/xing20a.html }, abstract = {Structured prediction of objects in spaces that are inherently difficult to search or compactly characterize is a particularly challenging task. For example, though bipartite matchings in two dimensions can be tractably optimized and learned, the higher-dimensional generalization—3D matchings—are NP-hard to optimally obtain and the set of potential solutions cannot be compactly characterized. Though approximation is therefore necessary, prevalent structured prediction methods inherit the weaknesses they possess in the two-dimensional setting either suffering from inconsistency or intractability—even when the approximations are sufficient. In this paper, we explore extending an adversarial approach to learning bipartite matchings that avoids these weaknesses to the three dimensional setting. We assess the benefits compared to margin-based methods on a three-frame tracking problem.} }
Endnote
%0 Conference Paper %T Adversarial Learning for 3D Matching %A Wei Xing %A Brian Ziebart %B Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI) %C Proceedings of Machine Learning Research %D 2020 %E Jonas Peters %E David Sontag %F pmlr-v124-xing20a %I PMLR %P 869--878 %U http://proceedings.mlr.press/v124/xing20a.html %V 124 %X Structured prediction of objects in spaces that are inherently difficult to search or compactly characterize is a particularly challenging task. For example, though bipartite matchings in two dimensions can be tractably optimized and learned, the higher-dimensional generalization—3D matchings—are NP-hard to optimally obtain and the set of potential solutions cannot be compactly characterized. Though approximation is therefore necessary, prevalent structured prediction methods inherit the weaknesses they possess in the two-dimensional setting either suffering from inconsistency or intractability—even when the approximations are sufficient. In this paper, we explore extending an adversarial approach to learning bipartite matchings that avoids these weaknesses to the three dimensional setting. We assess the benefits compared to margin-based methods on a three-frame tracking problem.
APA
Xing, W. & Ziebart, B.. (2020). Adversarial Learning for 3D Matching. Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI), in Proceedings of Machine Learning Research 124:869-878 Available from http://proceedings.mlr.press/v124/xing20a.html .

Related Material