Efficient grouping for keypoint detection
It addresses efficiency issues in keypoint detection for computer vision applications, but is incremental as it builds on the CenterNet architecture.
This paper tackles the challenge of high memory consumption and slow processing in keypoint detection on large datasets like DeepFashion2 by proposing an automatic grouping technique with post-processing, reducing memory use by up to 19% and processing time by up to 30% during inference without accuracy loss.
The success of deep neural networks in the traditional keypoint detection task encourages researchers to solve new problems and collect more complex datasets. The size of the DeepFashion2 dataset poses a new challenge on the keypoint detection task, as it comprises 13 clothing categories that span a wide range of keypoints (294 in total). The direct prediction of all keypoints leads to huge memory consumption, slow training, and a slow inference time. This paper studies the keypoint grouping approach and how it affects the performance of the CenterNet architecture. We propose a simple and efficient automatic grouping technique with a powerful post-processing method and apply it to the DeepFashion2 fashion landmark task and the MS COCO pose estimation task. This reduces memory consumption and processing time during inference by up to 19% and 30% respectively, and during the training stage by 28% and 26% respectively, without compromising accuracy.