Single-fusion detector: Towards faster multi-scale object detection
Despite recent improvements, the arbitrary sizes of objects still impede the predictive ability of object detectors. Recent solutions combine feature maps of different receptive fields to detect multi-scale objects. However, these methods have large computational costs resulting to slower inference ti...
Saved in:
| Main Author: | |
|---|---|
| Format: | text |
| Language: | English |
| Published: |
Animo Repository
2019
|
| Subjects: | |
| Online Access: | https://animorepository.dlsu.edu.ph/etd_masteral/6609 https://animorepository.dlsu.edu.ph/context/etd_masteral/article/13597/viewcontent/Antioquia__Arren_Matthew_Capuchino2___Single_Fusion_Detector_Towards_Faster_Multi_Scale_Object_Detection___ANTIOQUIA_Redacted.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | De La Salle University |
| Language: | English |
| Summary: | Despite recent improvements, the arbitrary sizes of objects still impede the predictive ability of object detectors. Recent solutions combine feature maps of different receptive fields to detect multi-scale objects. However, these methods have large computational costs resulting to slower inference time, which is not practical for real-time applications. Contrarily, fusion methods depending on large networks with many skip connections require larger memory footprint, prohibiting usage in devices with limited memory. In this paper, we propose a simpler novel fusion method which integrates multiple feature maps using a single concatenation operation. Our method can flexibly adapt to any base network, allowing for tailored performance for different computational requirements. Our approach achieves 81.7% mAP at 41 FPS on the PASCAL VOC dataset using ResNet-50 as the base network, which is superior in terms of both speed and mAP as compared to several state-of-the-art baselines that uses larger base networks. |
|---|