2018

SNIPER: Efficient Multi-Scale Training

Singh, Bharat, Najibi, Mahyar, Davis, Larry S.

Understand

We present SNIPER, an algorithm for performing efficient multi-scale training in instance level visual recognition tasks.

Instead of processing every pixel in an image pyramid, SNIPER processes context regions around ground-truth instances (referred to as chips) at the appropriate scale.
For background sampling, these context-regions are generated using proposals extracted from a region proposal network trained with a short learning schedule.
Hence, the number of chips generated per image during training adaptively changes based on the scene complexity.

Built on

Gradient-based learning applied to document recognition
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner · 1998
Earlier work this paper cites.
The dynamic representation of scenes
R. A. Rensink · 2000
Earlier work this paper cites.
Control of goal-directed and stimulus-driven attention in the brain
M. Corbetta and G. L. Shulman · 2002
Earlier work this paper cites.
Selective search for object recognition
J. R. Uijlings, K. E. Van De Sande, T. Gevers, and A. W. Smeulders · 2013
Earlier work this paper cites.
Rich feature hierarchies for accurate object detection and semantic segmentation
R. Girshick, J. Donahue, T. Darrell, and J. Malik · 2014
Earlier work this paper cites.
Spatial pyramid pooling in deep convolutional networks for visual recognition
K. He, X. Zhang, S. Ren, and J. Sun · 2014
Earlier work this paper cites.
The role of context for object detection and semantic segmentation in the wild
R. Mottaghi, X. Chen, X. Liu, N.-G. Cho, S.-W. Lee, S. Fidler, R. Urtasun, and A. Yuille · 2014
Earlier work this paper cites.
Edge boxes: Locating object proposals from edges
C. L. Zitnick and P. Dollár · 2014
Earlier work this paper cites.
Fast r-cnn
R. Girshick · 2015
Earlier work this paper cites.
Distilling the knowledge in a neural network
Original
G. Hinton, O. Vinyals, and J. Dean · 2015
Earlier work this paper cites.
Batch normalization: Accelerating deep network training by reducing internal covariate shift
S. Ioffe and C. Szegedy · 2015
Earlier work this paper cites.
Faster r-cnn: Towards real-time object detection with region proposal networks
S. Ren, K. He, R. Girshick, and J. Sun · 2015
Earlier work this paper cites.
Multi-scale context aggregation by dilated convolutions
Original
F. Yu and V. Koltun · 2015
Earlier work this paper cites.
Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks
S. Bell, C. Lawrence Zitnick, K. Bala, and R. Girshick · 2016
Earlier work this paper cites.

Similar

A unified multi-scale deep convolutional neural network for fast object detection
Z. Cai, Q. Fan, R. S. Feris, and N. Vasconcelos · 2016
Cited alongside, same era.
Locnet: Improving localization accuracy for object detection
S. Gidaris and N. Komodakis · 2016
Cited alongside, same era.
Deep residual learning for image recognition
K. He, X. Zhang, S. Ren, and J. Sun · 2016
Cited alongside, same era.
Identity mappings in deep residual networks
K. He, X. Zhang, S. Ren, and J. Sun · 2016
Cited alongside, same era.
Ssd: Single shot multibox detector
W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg · 2016
Cited alongside, same era.
Understanding the effective receptive field in deep convolutional neural networks
W. Luo, Y. Li, R. Urtasun, and R. Zemel · 2016
Cited alongside, same era.
Training region-based object detectors with online hard example mining
A. Shrivastava, A. Gupta, and R. Girshick · 2016
Cited alongside, same era.
Exploit all the layers: Fast and accurate cnn object detector with scale dependent pooling and cascaded rejection classifiers
F. Yang, W. Choi, and Y. Lin · 2016
Cited alongside, same era.
A multipath network for object detection
S. Zagoruyko, A. Lerer, T.-Y. Lin, P. O. Pinheiro, S. Gross, S. Chintala, and P. Dollar · 2016
Cited alongside, same era.
Sampling rate distortion
V. P. Boda and P. Narayan · 2017
Cited alongside, same era.
Soft-nms—improving object detection with one line of code
N. Bodla, B. Singh, R. Chellappa, and L. S. Davis · 2017
Cited alongside, same era.
Xception: Deep learning with depthwise separable convolutions
F. Chollet · 2017
Cited alongside, same era.

Then

Openimages: A public dataset for large-scale multi-label and multi-class image classification
I. Krasin, T. Duerig, N. Alldrin, V. Ferrari, S. Abu-El-Haija, A. Kuznetsova, H. Rom, J. Uijlings, S. Popov, S. Kamali, M. Malloci, J. Pont-Tuset, A. Veit, S. Belongie, V. Gomes, A. Gupta, C. Sun, G. Chechik, D. Cai, Z. Feng, D. Narayanan, and K. Murphy · 2017
Later among the works it cites.
Feature pyramid networks for object detection
T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie · 2017
Later among the works it cites.
SSH: Single stage headless face detector
M. Najibi, P. Samangouei, R. Chellappa, and L. Davis · 2017
Later among the works it cites.
Aggregated residual transformations for deep neural networks
S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. He · 2017
Later among the works it cites.
Crafting gbd-net for object detection
X. Zeng, W. Ouyang, J. Yan, H. Li, T. Xiao, K. Wang, Y. Liu, Y. Zhou, B. Yang, Z. Wang, et al · 2017
Later among the works it cites.
Pyramid scene parsing network
H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia · 2017
Later among the works it cites.
Universal sampling rate distortion
V. P. Boda and P. Narayan · 2018
Closest in time.
Focal loss for dense object detection
T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár · 2018
Closest in time.
Path aggregation network for instance segmentation
S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia · 2018
Closest in time.
Mixed precision training
S. Narang, G. Diamos, E. Elsen, P. Micikevicius, J. Alben, D. Garcia, B. Ginsburg, M. Houston, O. Kuchaiev, G. Venkatesh, et al · 2018
Closest in time.
Megdet: A large mini-batch object detector
C. Peng, T. Xiao, Z. Li, Y. Jiang, X. Zhang, K. Jia, G. Yu, and J. Sun · 2018
Closest in time.
Mobilenetv2: Inverted residuals and linear bottlenecks
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen · 2018
Closest in time.
An analysis of scale invariance in object detection-snip
B. Singh and L. S. Davis · 2018
Closest in time.
Group normalization
Original
Y. Wu and K. He · 2018
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…