Associative Embedding: End-to-End Learning for Joint Detection and Grouping
This addresses the need for more efficient and integrated solutions in computer vision applications, though it is incremental as it builds on existing network architectures.
The paper tackles the problem of joint detection and grouping in computer vision tasks like multi-person pose estimation and instance segmentation by introducing associative embedding, a method that enables networks to output detections and group assignments simultaneously, achieving state-of-the-art performance on MPII and MS-COCO datasets.
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.