.png){kind=icon}
Return
Exploring Dual Coupledness for Effective Pruning in Object Detection
.png){kind=icon}
OA
AI
DOI：10.1007/s11063-024-11697-8.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Pruning offers an efficient approach to compressing models deployed on resource-constrained devices. In this paper, we introduce a novel method called Dual-Coupledness Object Detection Pruning (DCODP), specifically designed for object detection models. Taking into account the complexity of model coupling, our algorithm utilizes a depth-first search approach to identify interlayer coupling within the model. It then groups sublayers with the same parent layer together. Filters corresponding to feature maps with strong coupling are pruned within the layer, and the same pruning operation is applied to the corresponding indices in other coupled layers. In order to prove the validity of our method, extensive experiments are conducted on PASCAL VOC2007, PASCAL VOC2012 and MS COCO2017. The results show that our DCODP achieves a significant reduction of 50% in parameters and an average of more than 70% impressive score.
Keywords:
Object detection
Model compression
Filter pruning
Coupling
Journal
IF:
2.8
Papers:
178
Citations:
5.5K
Organization
Cited Papers
.png){kind=icon}
ShareSave
ShareSaveShareSaveShareSave
View more