You Only Look Once at Anytime (AnytimeYOLO): Analysis and Optimization of Early-Exits for Object-Detection
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_ | 1866917964920389632 |
|---|---|
| author | Kuhse, Daniel Teper, Harun Buschjäger, Sebastian Wang, Chien-Yao Chen, Jian-Jia |
| author_facet | Kuhse, Daniel Teper, Harun Buschjäger, Sebastian Wang, Chien-Yao Chen, Jian-Jia |
| contents | We introduce AnytimeYOLO, a family of variants of the YOLO architecture that enables anytime object detection. Our AnytimeYOLO networks allow for interruptible inference, i.e., they provide a prediction at any point in time, a property desirable for safety-critical real-time applications.
We present structured explorations to modify the YOLO architecture, enabling early termination to obtain intermediate results. We focus on providing fine-grained control through high granularity of available termination points. First, we formalize Anytime Models as a special class of prediction models that offer anytime predictions. Then, we discuss a novel transposed variant of the YOLO architecture, that changes the architecture to enable better early predictions and greater freedom for the order of processing stages. Finally, we propose two optimization algorithms that, given an anytime model, can be used to determine the optimal exit execution order and the optimal subset of early-exits to select for deployment in low-resource environments. We evaluate the anytime performance and trade-offs of design choices, proposing a new anytime quality metric for this purpose. In particular, we also discuss key challenges for anytime inference that currently make its deployment costly. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17497 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | You Only Look Once at Anytime (AnytimeYOLO): Analysis and Optimization of Early-Exits for Object-Detection Kuhse, Daniel Teper, Harun Buschjäger, Sebastian Wang, Chien-Yao Chen, Jian-Jia Computer Vision and Pattern Recognition Machine Learning We introduce AnytimeYOLO, a family of variants of the YOLO architecture that enables anytime object detection. Our AnytimeYOLO networks allow for interruptible inference, i.e., they provide a prediction at any point in time, a property desirable for safety-critical real-time applications. We present structured explorations to modify the YOLO architecture, enabling early termination to obtain intermediate results. We focus on providing fine-grained control through high granularity of available termination points. First, we formalize Anytime Models as a special class of prediction models that offer anytime predictions. Then, we discuss a novel transposed variant of the YOLO architecture, that changes the architecture to enable better early predictions and greater freedom for the order of processing stages. Finally, we propose two optimization algorithms that, given an anytime model, can be used to determine the optimal exit execution order and the optimal subset of early-exits to select for deployment in low-resource environments. We evaluate the anytime performance and trade-offs of design choices, proposing a new anytime quality metric for this purpose. In particular, we also discuss key challenges for anytime inference that currently make its deployment costly. |
| title | You Only Look Once at Anytime (AnytimeYOLO): Analysis and Optimization of Early-Exits for Object-Detection |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2503.17497 |