Associative Embedding: End-to-End Learning for Joint Detection and Grouping

Code

• github.com/open-mmlab/mmpose
  pytorch★ 7,439
• github.com/princeton-vl/pose-ae-train
  pytorch★ 0
• github.com/baodi23/hourglass-facekeypoints-detection
  pytorch★ 0
• github.com/raymon-tian/hourglass-facekeypoints-detection
  pytorch★ 0
• github.com/stevehjc/pose-ae-demo-tf
  tf★ 0

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 both multi-person pose estimation and instance segmentation and report state-of-the-art performance for multi-person pose on the MPII and MS-COCO datasets.

Tasks

Benchmark Results

Reproductions