.png){kind=icon}
.png){kind=icon}
Return
TA-BiDet: Task-aligned binary object detector
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2022.09.038.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Binary CNN-based object detector, largely saving storage and computation costs, has received high atten-tion recently for the potention of efficient deployment on resource-constrained devices. However, previ-ous designs often suffer from significant accuracy loss when compared to their real-value counterparts. This study demonstrates that the primary reason lies in the mis-alignment of the classification and regression tasks, which is generally caused by the limited representational capacity of the binary neural network and biased training procedures used in traditional detection frameworks. Based on this observa-tion, we propose TA-BiDet (Task-Alignment Binary object Detection) that can guarantee aligned training of the two tasks by adopting a task-aware feature disentanglement (TFD) network architecture with an alignment-oriented learning (AOL) approach. The proposed approaches can ensure more informative and tailored task-specific features to be learned jointly for each task and select the most accurate detected boxes with both high confidence scores and precise locations. Experiments on the PASCAL VOC and COCO datasets have shown that TA-BiDet outperformed state-of-the-art binary object detectors by a con-siderable margin. Moreover, TA-BiDet has successfully narrowed the performance gap with the real-valued SSD300 detector to only 0.7% in terms of mAP, and reduced the model size by 4.86x and the total OPs by 9.89x, respectively.(c) 2022 Elsevier B.V. All rights reserved.
Keywords:
Binary neural networks
Object detection
Task-aware feature disentanglement
Alignment-oriented learning