Jun Wang, Rongrong Ji, Shouhong Ding, Jie Hu, Lei Shen, Liujuan Cao, Shengchuan Zhang, Yingyi Zhang, Suhang Ye
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In the field of human pose estimation, regression-based methods have been dominated in terms of speed, while heatmap-based methods are far ahead in terms of performance. How to take advantage of both schemes remains a challenging problem. In this paper, we propose a novel human pose estimation framework termed Distil-Pose, which DistilPose-S obtains 71.6% mAP with 5. 36M parameters, 2.38 GFLOPs, and 40.2 FPS, which saves 12.95×, 7.16× computational cost and is 4.9× faster than its teacher model with only 0.9 points performance drop. Furthermore, DistilPose-L obtains 74.4% mAP on MSCOCO validation dataset, achieving a new state-of-the-art among predominant regression-based models. Code will be available at https://github.com/yshMars/DistilPose.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.02455")
get_code_for_paper("2303.02455")
have("2303.02455")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2303.02455.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2303.02455)
Connect an agent — have() is free.