EffiPerception: an Efficient Framework for Various Perception Tasks
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_ | 1866917617898356736 |
|---|---|
| author | Xiang, Xinhao Dräger, Simon Zhang, Jiawei |
| author_facet | Xiang, Xinhao Dräger, Simon Zhang, Jiawei |
| contents | The accuracy-speed-memory trade-off is always the priority to consider for several computer vision perception tasks.
Previous methods mainly focus on a single or small couple of these tasks, such as creating effective data augmentation, feature extractor, learning strategies, etc. These approaches, however, could be inherently task-specific: their proposed model's performance may depend on a specific perception task or a dataset.
Targeting to explore common learning patterns and increasing the module robustness, we propose the EffiPerception framework.
It could achieve great accuracy-speed performance with relatively low memory cost under several perception tasks: 2D Object Detection, 3D Object Detection, 2D Instance Segmentation, and 3D Point Cloud Segmentation.
Overall, the framework consists of three parts:
(1) Efficient Feature Extractors, which extract the input features for each modality. (2) Efficient Layers, plug-in plug-out layers that further process the feature representation, aggregating core learned information while pruning noisy proposals. (3) The EffiOptim, an 8-bit optimizer to further cut down the computational cost and facilitate performance stability.
Extensive experiments on the KITTI, semantic-KITTI, and COCO datasets revealed that EffiPerception could show great accuracy-speed-memory overall performance increase within the four detection and segmentation tasks, in comparison to earlier, well-respected methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12317 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EffiPerception: an Efficient Framework for Various Perception Tasks Xiang, Xinhao Dräger, Simon Zhang, Jiawei Computer Vision and Pattern Recognition The accuracy-speed-memory trade-off is always the priority to consider for several computer vision perception tasks. Previous methods mainly focus on a single or small couple of these tasks, such as creating effective data augmentation, feature extractor, learning strategies, etc. These approaches, however, could be inherently task-specific: their proposed model's performance may depend on a specific perception task or a dataset. Targeting to explore common learning patterns and increasing the module robustness, we propose the EffiPerception framework. It could achieve great accuracy-speed performance with relatively low memory cost under several perception tasks: 2D Object Detection, 3D Object Detection, 2D Instance Segmentation, and 3D Point Cloud Segmentation. Overall, the framework consists of three parts: (1) Efficient Feature Extractors, which extract the input features for each modality. (2) Efficient Layers, plug-in plug-out layers that further process the feature representation, aggregating core learned information while pruning noisy proposals. (3) The EffiOptim, an 8-bit optimizer to further cut down the computational cost and facilitate performance stability. Extensive experiments on the KITTI, semantic-KITTI, and COCO datasets revealed that EffiPerception could show great accuracy-speed-memory overall performance increase within the four detection and segmentation tasks, in comparison to earlier, well-respected methods. |
| title | EffiPerception: an Efficient Framework for Various Perception Tasks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.12317 |