RSPose: Ranking Based Losses for Human Pose Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917086481088512 |
|---|---|
| author | Keles, Muhammed Can Cetinkaya, Bedrettin Kalkan, Sinan Akbas, Emre |
| author_facet | Keles, Muhammed Can Cetinkaya, Bedrettin Kalkan, Sinan Akbas, Emre |
| contents | While heatmap-based human pose estimation methods have shown strong performance, they suffer from three main problems: (P1) "Commonly used Mean Squared Error (MSE)" Loss may not always improve joint localization because it penalizes all pixel deviations equally, without focusing explicitly on sharpening and correctly localizing the peak corresponding to the joint; (P2) heatmaps are spatially and class-wise imbalanced; and, (P3) there is a discrepancy between the evaluation metric (i.e., mAP) and the loss functions.
We propose ranking-based losses to address these issues.
Both theoretically and empirically, we show that our proposed losses are superior to commonly used heatmap losses (MSE, KL-Divergence). Our losses considerably increase the correlation between confidence scores and localization qualities, which is desirable because higher correlation leads to more accurate instance selection during Non-Maximum Suppression (NMS) and better Average Precision (mAP) performance. We refer to the models trained with our losses as RSPose.
We show the effectiveness of RSPose across two different modes: one-dimensional and two-dimensional heatmaps, on three different datasets (COCO, CrowdPose, MPII).
To the best of our knowledge, we are the first to propose losses that align with the evaluation metric (mAP) for human pose estimation.
RSPose outperforms the previous state of the art on the COCO-val set and achieves an mAP score of 79.9 with ViTPose-H, a vision transformer model for human pose estimation.
We also improve SimCC Resnet-50, a coordinate classification-based pose estimation method, by 1.5 AP on the COCO-val set, achieving 73.6 AP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_13857 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RSPose: Ranking Based Losses for Human Pose Estimation Keles, Muhammed Can Cetinkaya, Bedrettin Kalkan, Sinan Akbas, Emre Computer Vision and Pattern Recognition While heatmap-based human pose estimation methods have shown strong performance, they suffer from three main problems: (P1) "Commonly used Mean Squared Error (MSE)" Loss may not always improve joint localization because it penalizes all pixel deviations equally, without focusing explicitly on sharpening and correctly localizing the peak corresponding to the joint; (P2) heatmaps are spatially and class-wise imbalanced; and, (P3) there is a discrepancy between the evaluation metric (i.e., mAP) and the loss functions. We propose ranking-based losses to address these issues. Both theoretically and empirically, we show that our proposed losses are superior to commonly used heatmap losses (MSE, KL-Divergence). Our losses considerably increase the correlation between confidence scores and localization qualities, which is desirable because higher correlation leads to more accurate instance selection during Non-Maximum Suppression (NMS) and better Average Precision (mAP) performance. We refer to the models trained with our losses as RSPose. We show the effectiveness of RSPose across two different modes: one-dimensional and two-dimensional heatmaps, on three different datasets (COCO, CrowdPose, MPII). To the best of our knowledge, we are the first to propose losses that align with the evaluation metric (mAP) for human pose estimation. RSPose outperforms the previous state of the art on the COCO-val set and achieves an mAP score of 79.9 with ViTPose-H, a vision transformer model for human pose estimation. We also improve SimCC Resnet-50, a coordinate classification-based pose estimation method, by 1.5 AP on the COCO-val set, achieving 73.6 AP. |
| title | RSPose: Ranking Based Losses for Human Pose Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.13857 |