Timezone: »
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.
Author Information
Alejandro Newell (University of Michigan)
Zhiao Huang (IIIS, Tsinghua University)
Jia Deng (University of Michigan)
More from the Same Authors
-
2018 Poster: Object-Oriented Dynamics Predictor »
Guangxiang Zhu · Zhiao Huang · Chongjie Zhang -
2017 Poster: Premise Selection for Theorem Proving by Deep Graph Embedding »
Mingzhe Wang · Yihe Tang · Jian Wang · Jia Deng -
2017 Spotlight: Premise Selection for Theorem Proving by Deep Graph Embedding »
Mingzhe Wang · Yihe Tang · Jian Wang · Jia Deng -
2017 Poster: Pixels to Graphs by Associative Embedding »
Alejandro Newell · Jia Deng -
2016 Poster: Single-Image Depth Perception in the Wild »
Weifeng Chen · Zhao Fu · Dawei Yang · Jia Deng -
2014 Workshop: Representation and Learning Methods for Complex Outputs »
Richard Zemel · Dale Schuurmans · Kilian Q Weinberger · Yuhong Guo · Jia Deng · Francesco Dinuzzo · Hal Daumé III · Honglak Lee · Noah A Smith · Richard Sutton · Jiaqian YU · Vitaly Kuznetsov · Luke Vilnis · Hanchen Xiong · Calvin Murdock · Thomas Unterthiner · Jean-Francis Roy · Martin Renqiang Min · Hichem SAHBI · Fabio Massimo Zanzotto