An Investigation on The Position Encoding in Vision-Based Dynamics Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912003728080896 |
|---|---|
| author | Zhu, Jiageng Xie, Hanchen Li, Jiazhi Khayatkhoei, Mahyar AbdAlmageed, Wael |
| author_facet | Zhu, Jiageng Xie, Hanchen Li, Jiazhi Khayatkhoei, Mahyar AbdAlmageed, Wael |
| contents | Despite the success of vision-based dynamics prediction models, which predict object states by utilizing RGB images and simple object descriptions, they were challenged by environment misalignments. Although the literature has demonstrated that unifying visual domains with both environment context and object abstract, such as semantic segmentation and bounding boxes, can effectively mitigate the visual domain misalignment challenge, discussions were focused on the abstract of environment context, and the insight of using bounding box as the object abstract is under-explored. Furthermore, we notice that, as empirical results shown in the literature, even when the visual appearance of objects is removed, object bounding boxes alone, instead of being directly fed into the network, can indirectly provide sufficient position information via the Region of Interest Pooling operation for dynamics prediction. However, previous literature overlooked discussions regarding how such position information is implicitly encoded in the dynamics prediction model. Thus, in this paper, we provide detailed studies to investigate the process and necessary conditions for encoding position information via using the bounding box as the object abstract into output features. Furthermore, we study the limitation of solely using object abstracts, such that the dynamics prediction performance will be jeopardized when the environment context varies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_15201 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An Investigation on The Position Encoding in Vision-Based Dynamics Prediction Zhu, Jiageng Xie, Hanchen Li, Jiazhi Khayatkhoei, Mahyar AbdAlmageed, Wael Computer Vision and Pattern Recognition Despite the success of vision-based dynamics prediction models, which predict object states by utilizing RGB images and simple object descriptions, they were challenged by environment misalignments. Although the literature has demonstrated that unifying visual domains with both environment context and object abstract, such as semantic segmentation and bounding boxes, can effectively mitigate the visual domain misalignment challenge, discussions were focused on the abstract of environment context, and the insight of using bounding box as the object abstract is under-explored. Furthermore, we notice that, as empirical results shown in the literature, even when the visual appearance of objects is removed, object bounding boxes alone, instead of being directly fed into the network, can indirectly provide sufficient position information via the Region of Interest Pooling operation for dynamics prediction. However, previous literature overlooked discussions regarding how such position information is implicitly encoded in the dynamics prediction model. Thus, in this paper, we provide detailed studies to investigate the process and necessary conditions for encoding position information via using the bounding box as the object abstract into output features. Furthermore, we study the limitation of solely using object abstracts, such that the dynamics prediction performance will be jeopardized when the environment context varies. |
| title | An Investigation on The Position Encoding in Vision-Based Dynamics Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.15201 |