Warp-Refine Propagation: Semi-Supervised Auto-labeling via Cycle-consistency

no code implementations • ICCV 2021 • Aditya Ganeshan, Alexis Vallet, Yasunori Kudo, Shin-ichi Maeda, Tommi Kerola, Rares Ambrus, Dennis Park, Adrien Gaidon

Deep learning models for semantic segmentation rely on expensive, large-scale, manually annotated datasets.

Segmentation Semantic Segmentation

Hierarchical Lovasz Embeddings for Proposal-Free Panoptic Segmentation

no code implementations • CVPR 2021 • Tommi Kerola, Jie Li, Atsushi Kanehira, Yasunori Kudo, Alexis Vallet, Adrien Gaidon

We use a hierarchical Lovasz hinge loss to learn a low-dimensional embedding space structured into a unified semantic and instance hierarchy without requiring separate network branches or object proposals.

Instance Segmentation Panoptic Segmentation +1

Hierarchical Lovász Embeddings for Proposal-free Panoptic Segmentation

no code implementations • 8 Jun 2021 • Tommi Kerola, Jie Li, Atsushi Kanehira, Yasunori Kudo, Alexis Vallet, Adrien Gaidon

We use a hierarchical Lov\'asz hinge loss to learn a low-dimensional embedding space structured into a unified semantic and instance hierarchy without requiring separate network branches or object proposals.

Instance Segmentation Panoptic Segmentation +1

Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations

no code implementations • 22 Mar 2018 • Yasunori Kudo, Keisuke Ogaki, Yusuke Matsui, Yuri Odagiri

Our method can predict a 3D pose from 2D joint locations in a single image.

3D Human Pose Estimation 3D Pose Estimation