2017

Focal Loss for Dense Object Detection

Lin, Tsung-Yi, Goyal, Priya, Girshick, Ross et al.

Understand

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations.

In contrast, one-stage detectors that are applied over a regular, dense sampling of possible object locations have the potential to be faster and simpler, but have trailed the accuracy of two-stage detectors thus far.
In this paper, we investigate why this is the case.
We discover that the extreme foreground-background class imbalance encountered during training of dense detectors is the central cause.

Built on

Backpropagation applied to handwritten zip code recognition
Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel · 1989
Earlier work this paper cites.
Learning and Example Selection for Object and Pattern Detection
K.-K. Sung and T. Poggio · 1994
Earlier work this paper cites.
Original approach for the localisation of objects in images
R. Vaillant, C. Monrocq, and Y. LeCun · 1994
Earlier work this paper cites.
Human face detection in visual scenes
H. Rowley, S. Baluja, and T. Kanade · 1995
Earlier work this paper cites.
Rapid object detection using a boosted cascade of simple features
P. Viola and M. Jones · 2001
Earlier work this paper cites.
Histograms of oriented gradients for human detection
N. Dalal and B. Triggs · 2005
Earlier work this paper cites.
The elements of statistical learning
T. Hastie, R. Tibshirani, and J. Friedman · 2008
Earlier work this paper cites.
Integral channel features
P. Dollár, Z. Tu, P. Perona, and S. Belongie · 2009
Earlier work this paper cites.
The PASCAL Visual Object Classes (VOC) Challenge
M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman · 2010
Earlier work this paper cites.
Cascade object detection with deformable part models
P. F. Felzenszwalb, R. B. Girshick, and D. McAllester · 2010
Earlier work this paper cites.
ImageNet classification with deep convolutional neural networks
A. Krizhevsky, I. Sutskever, and G. Hinton · 2012
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.
Scalable object detection using deep neural networks
D. Erhan, C. Szegedy, A. Toshev, and D. Anguelov · 2014
Earlier work this paper cites.

Similar

Rich feature hierarchies for accurate object detection and semantic segmentation
R. Girshick, J. Donahue, T. Darrell, and J. Malik · 2014
Cited alongside, same era.
Spatial pyramid pooling in deep convolutional networks for visual recognition
K. He, X. Zhang, S. Ren, and J. Sun · 2014
Cited alongside, same era.
Microsoft COCO: Common objects in context
T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick · 2014
Cited alongside, same era.
Overfeat: Integrated recognition, localization and detection using convolutional networks
P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. LeCun · 2014
Cited alongside, same era.
Edge boxes: Locating object proposals from edges
C. L. Zitnick and P. Dollár · 2014
Cited alongside, same era.
Fast R-CNN
R. Girshick · 2015
Cited alongside, same era.
Fully convolutional networks for semantic segmentation
J. Long, E. Shelhamer, and T. Darrell · 2015
Cited alongside, same era.
Learning to segment object candidates
P. O. Pinheiro, R. Collobert, and P. Dollar · 2015
Cited alongside, same era.
Faster R-CNN: Towards real-time object detection with region proposal networks
S. Ren, K. He, R. Girshick, and J. Sun · 2015
Cited alongside, same era.
Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks
S. Bell, C. L. Zitnick, K. Bala, and R. Girshick · 2016
Cited alongside, same era.
R-FCN: Object detection via region-based fully convolutional networks
J. Dai, Y. Li, K. He, and J. Sun · 2016
Cited alongside, same era.
DSSD: Deconvolutional single shot detector
Original
C.-Y. Fu, W. Liu, A. Ranga, A. Tyagi, and A. C. Berg · 2016
Cited alongside, same era.

Then

SSD: Single shot multibox detector
W. Liu, D. Anguelov, D. Erhan, C. Szegedy, and S. Reed · 2016
Later among the works it cites.
Learning to refine object segments
P. O. Pinheiro, T.-Y. Lin, R. Collobert, and P. Dollár · 2016
Later among the works it cites.
You only look once: Unified, real-time object detection
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi · 2016
Later among the works it cites.
Training region-based object detectors with online hard example mining
A. Shrivastava, A. Gupta, and R. Girshick · 2016
Later among the works it cites.
Beyond skip connections: Top-down modulation for object detection
Original
A. Shrivastava, R. Sukthankar, J. Malik, and A. Gupta · 2016
Later among the works it cites.
Loss max-pooling for semantic image segmentation
S. R. Bulo, G. Neuhold, and P. Kontschieder · 2017
Closest in time.
Mask R-CNN
K. He, G. Gkioxari, P. Dollár, and R. Girshick · 2017
Closest in time.
Speed/accuracy trade-offs for modern convolutional object detectors
J. Huang, V. Rathod, C. Sun, M. Zhu, A. Korattikara, A. Fathi, I. Fischer, Z. Wojna, Y. Song, S. Guadarrama, and K. Murphy · 2017
Closest in time.
Feature pyramid networks for object detection
T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie · 2017
Closest in time.
YOLO9000: Better, faster, stronger
J. Redmon and A. Farhadi · 2017
Closest in time.
Inception-v4, inception-resnet and the impact of residual connections on learning
C. Szegedy, S. Ioffe, V. Vanhoucke, and A. A. Alemi · 2017
Closest in time.
Aggregated residual transformations for deep neural networks
S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. He · 2017
Closest in time.
Detectron
R. Girshick, I. Radosavovic, G. Gkioxari, P. Dollár, 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…