TY - GEN
T1 - Surprisingly Easy Network Compression and Data Extension for Object Instance Detection
AU - Wang, Rui
AU - Xu, Jingwen
AU - Han, Tony X.
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/7/2
Y1 - 2018/7/2
N2 - To detect instances in unstructured environment with mobile system, we develop a light weight but accurate learning model denoted as B-PA(BING Pruned Alexnet). Our method first utilizes BING(Binarized Normed Gradient) to compute bounding boxes, then builds a compressed network for recognition by pruning neurons and cutting fully connected layers on the original noted Alexnet. Addressing the problem that the training samples for instance detection are limited and of small variation, we extend the training data by combining data augmentation with synthetic generation. Our B-PA model takes only 5.3MB, which is 50 times smaller but with equivalent or even higher accuracy than the original Alexnet. Experiment results demonstrate that our method outperforms the state-of-art instance detection algorithms on WRGB-D Dataset and GMU Kitchen Dataset.
AB - To detect instances in unstructured environment with mobile system, we develop a light weight but accurate learning model denoted as B-PA(BING Pruned Alexnet). Our method first utilizes BING(Binarized Normed Gradient) to compute bounding boxes, then builds a compressed network for recognition by pruning neurons and cutting fully connected layers on the original noted Alexnet. Addressing the problem that the training samples for instance detection are limited and of small variation, we extend the training data by combining data augmentation with synthetic generation. Our B-PA model takes only 5.3MB, which is 50 times smaller but with equivalent or even higher accuracy than the original Alexnet. Experiment results demonstrate that our method outperforms the state-of-art instance detection algorithms on WRGB-D Dataset and GMU Kitchen Dataset.
KW - Bi-narised Normed Gradient
KW - Data Extension; Synthetic generation
KW - Object Instance Detection
KW - Pruned Alexnet
UR - https://www.scopus.com/pages/publications/85065436397
U2 - 10.1109/VCIP.2018.8698673
DO - 10.1109/VCIP.2018.8698673
M3 - 会议稿件
AN - SCOPUS:85065436397
T3 - VCIP 2018 - IEEE International Conference on Visual Communications and Image Processing
BT - VCIP 2018 - IEEE International Conference on Visual Communications and Image Processing
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 33rd IEEE International Conference on Visual Communications and Image Processing, VCIP 2018
Y2 - 9 December 2018 through 12 December 2018
ER -