TY - GEN
T1 - Assisted excitation of activations
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
AU - Derakhshani, Mohammad Mahdi
AU - Masoudnia, Saeed
AU - Shaker, Amir Hossein
AU - Mersa, Omid
AU - Sadeghi, Mohammad Amin
AU - Rastegari, Mohammad
AU - Araabi, Babak N.
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - We present a simple yet effective learning technique that significantly improves mAP of YOLO object detectors without compromising their speed. During network training, we carefully feed in localization information. We excite certain activations in order to help the network learn to better localize (Figure 2). In the later stages of training, we gradually reduce our assisted excitation to zero. We reached a new state-of-the-art in the speed-accuracy trade-off (Figure 1). Our technique improves the mAP of YOLOv2 by 3.8% and mAP of YOLOv3 by 2.2% on MSCOCO dataset. This technique is inspired from curriculum learning. It is simple and effective and it is applicable to most single-stage object detectors.
AB - We present a simple yet effective learning technique that significantly improves mAP of YOLO object detectors without compromising their speed. During network training, we carefully feed in localization information. We excite certain activations in order to help the network learn to better localize (Figure 2). In the later stages of training, we gradually reduce our assisted excitation to zero. We reached a new state-of-the-art in the speed-accuracy trade-off (Figure 1). Our technique improves the mAP of YOLOv2 by 3.8% and mAP of YOLOv3 by 2.2% on MSCOCO dataset. This technique is inspired from curriculum learning. It is simple and effective and it is applicable to most single-stage object detectors.
KW - Categorization
KW - Computer Vision Theory
KW - Datasets and Evaluation
KW - Deep Learning
KW - Recognition: Detection
KW - Retrieval
UR - http://www.scopus.com/inward/record.url?scp=85078791207&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2019.00942
DO - 10.1109/CVPR.2019.00942
M3 - Conference contribution
AN - SCOPUS:85078791207
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 9193
EP - 9202
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PB - IEEE Computer Society
Y2 - 16 June 2019 through 20 June 2019
ER -