TY - JOUR
T1 - NAS-FCOS
T2 - Efficient Search for Object Detection Architectures
AU - Wang, Ning
AU - Gao, Yang
AU - Chen, Hao
AU - Wang, Peng
AU - Tian, Zhi
AU - Shen, Chunhua
AU - Zhang, Yanning
N1 - Publisher Copyright:
© 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2021/12
Y1 - 2021/12
N2 - Neural Architecture Search (NAS) has shown great potential in effectively reducing manual effort in network design by automatically discovering optimal architectures. What is noteworthy is that as of now, object detection is less touched by NAS algorithms despite its significant importance in computer vision. To the best of our knowledge, most of the recent NAS studies on object detection tasks fail to satisfactorily strike a balance between performance and efficiency of the resulting models, let alone the excessive amount of computational resources cost by those algorithms. Here we propose an efficient method to obtain better object detectors by searching for the feature pyramid network as well as the prediction head of a simple anchor-free object detector, namely, FCOS (Tian et al. in FCOS: Fully convolutional one-stage object detection, 2019), using a tailored reinforcement learning paradigm. With carefully designed search space, search algorithms, and strategies for evaluating network quality, we are able to find top-performing detection architectures within 4 days using 8 V100 GPUs. The discovered architectures surpass state-of-the-art object detection models (such as Faster R-CNN, RetinaNet and, FCOS) by 1.0 to 5.4% points in AP on the COCO dataset, with comparable computation complexity and memory footprint, demonstrating the efficacy of the proposed NAS method for object detection. Code is available at https://github.com/Lausannen/NAS-FCOS.
AB - Neural Architecture Search (NAS) has shown great potential in effectively reducing manual effort in network design by automatically discovering optimal architectures. What is noteworthy is that as of now, object detection is less touched by NAS algorithms despite its significant importance in computer vision. To the best of our knowledge, most of the recent NAS studies on object detection tasks fail to satisfactorily strike a balance between performance and efficiency of the resulting models, let alone the excessive amount of computational resources cost by those algorithms. Here we propose an efficient method to obtain better object detectors by searching for the feature pyramid network as well as the prediction head of a simple anchor-free object detector, namely, FCOS (Tian et al. in FCOS: Fully convolutional one-stage object detection, 2019), using a tailored reinforcement learning paradigm. With carefully designed search space, search algorithms, and strategies for evaluating network quality, we are able to find top-performing detection architectures within 4 days using 8 V100 GPUs. The discovered architectures surpass state-of-the-art object detection models (such as Faster R-CNN, RetinaNet and, FCOS) by 1.0 to 5.4% points in AP on the COCO dataset, with comparable computation complexity and memory footprint, demonstrating the efficacy of the proposed NAS method for object detection. Code is available at https://github.com/Lausannen/NAS-FCOS.
KW - Deep learning
KW - Neural architecture search
KW - Object detection
KW - Reinforcement learning
UR - http://www.scopus.com/inward/record.url?scp=85117146917&partnerID=8YFLogxK
U2 - 10.1007/s11263-021-01523-2
DO - 10.1007/s11263-021-01523-2
M3 - 文章
AN - SCOPUS:85117146917
SN - 0920-5691
VL - 129
SP - 3299
EP - 3312
JO - International Journal of Computer Vision
JF - International Journal of Computer Vision
IS - 12
ER -