semi-supervised
Papers with tag semi-supervised
2022
2021
- Semi-supervised Dense Keypointsusing Unlabeled Multiview ImagesZhixuan Yu, Haozheng Yu, Long Sha, Sujoy Ganguly, and Hyun Soo ParkIn 2021
This paper presents a new end-to-end semi-supervised framework to learn adense keypoint detector using unlabeled multiview images. A key challenge liesin finding the exact correspondences between the dense keypoints in multipleviews since the inverse of keypoint mapping can be neither analytically derivednor differentiated. This limits applying existing multiview supervisionapproaches on sparse keypoint detection that rely on the exact correspondences.To address this challenge, we derive a new probabilistic epipolar constraintthat encodes the two desired properties. (1) Soft correspondence: we define amatchability, which measures a likelihood of a point matching to the otherimage’s corresponding point, thus relaxing the exact correspondences’requirement. (2) Geometric consistency: every point in the continuouscorrespondence fields must satisfy the multiview consistency collectively. Weformulate a probabilistic epipolar constraint using a weighted average ofepipolar errors through the matchability thereby generalizing thepoint-to-point geometric error to the field-to-field geometric error. Thisgeneralization facilitates learning a geometrically coherent dense keypointdetection model by utilizing a large number of unlabeled multiview images.Additionally, to prevent degenerative cases, we employ a distillation-basedregularization by using a pretrained model. Finally, we design a new neuralnetwork architecture, made of twin networks, that effectively minimizes theprobabilistic epipolar errors of all possible correspondences between two viewimages by building affinity matrices. Our method shows superior performancecompared to existing methods, including non-differentiable bootstrapping interms of keypoint accuracy, multiview consistency, and 3D reconstructionaccuracy.
提出了软的对应关系通过几何一致性来约束
human mv 1p densepose semi-supervised@inproceedings{semidense, title = {Semi-supervised Dense Keypointsusing Unlabeled Multiview Images}, author = {Yu, Zhixuan and Yu, Haozheng and Sha, Long and Ganguly, Sujoy and Park, Hyun Soo}, year = {2021}, tags = {human, mv, 1p, densepose, semi-supervised}, }