`

Timezone: »

 
Poster
An Empirical Study of Adder Neural Networks for Object Detection
Xinghao Chen · Chang Xu · Minjing Dong · Chunjing XU · Yunhe Wang

Wed Dec 08 12:30 AM -- 02:00 AM (PST) @ None #None
Adder neural networks (AdderNets) have shown impressive performance on image classification with only addition operations, which are more energy efficient than traditional convolutional neural networks built with multiplications. Compared with classification, there is a strong demand on reducing the energy consumption of modern object detectors via AdderNets for real-world applications such as autonomous driving and face detection. In this paper, we present an empirical study of AdderNets for object detection. We first reveal that the batch normalization statistics in the pre-trained adder backbone should not be frozen, since the relatively large feature variance of AdderNets. Moreover, we insert more shortcut connections in the neck part and design a new feature fusion architecture for avoiding the sparse features of adder layers. We present extensive ablation studies to explore several design choices of adder detectors. Comparisons with state-of-the-arts are conducted on COCO and PASCAL VOC benchmarks. Specifically, the proposed Adder FCOS achieves a 37.8% AP on the COCO val set, demonstrating comparable performance to that of the convolutional counterpart with an about $1.4\times$ energy reduction.

Author Information

Xinghao Chen (Huawei Noah's Ark Lab)
Chang Xu (The University of Sydney)
Minjing Dong (University of Sydney)
Chunjing XU (Huawei Technologies)
Yunhe Wang (Huawei Noah's Ark Lab)

More from the Same Authors