Associative Embedding: End-to-End Learning for Joint Detection and Grouping
Published in
Neural Information Processing Systems(2016)External Links:
TL
TL;DR
Associative embedding is introduced, a novel method for supervising convolutional neural networks for the task of detection and grouping for multi-person pose estimation and state-of-the-art performance on the MPII and MS-COCO datasets is reported.
Abstract
We introduce associative embedding, a novel method for supervising convolutional neural networks for the task of detection and grouping. A number of computer vision problems can be framed in this manner including multi-person pose estimation, instance segmentation, and multi-object tracking. Usually the grouping of detections is achieved with multi-stage pipelines, instead we propose an approach that teaches a network to simultaneously output detections and group assignments. This technique can be easily integrated into any state-of-the-art network architecture that produces pixel-wise predictions. We show how to apply this method to multi-person pose estimation and report state-of-the-art performance on the MPII and MS-COCO datasets.
References54 items
1
Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation
2
Mask R-CNN
3
Multi-context Attention for Human Pose Estimation
4
Towards Accurate Multi-person Pose Estimation in the Wild
5