1. BING: Binarized Normed Gradients for Objectness Estimation at 300fps
CVPR 2014 Oral

2. Outline
1. Introduction
2. Methodology 2.1 Normed gradients (NG) and objectness 2.2 Learning objectness measurement with NG 2.3 Binarized normed gradients (BING)
3. Experimental Evaluation
4. Conclusion and Future Work

3. 1. Introduction
＊Motivation: Generic object detection

4. 1. Introduction
objectness measure which is generic over categories has recently becomes popular

5. 1. Introduction
＊Objectness : is a value which reflects how likely an image window covers an object of any category[3]
computational efficiency
improve
detection accuracy
＊What is a good objectness measure?
Achieve high object detection rate (DR)
Produce a small number of proposals
Obtain high computational efficiency
Have good generalization ability to unseen object categories

6. 1. Introduction
＊we propose a surprisingly simple and powerful feature “BING” to help the search for objects using objectness scores
＊We observe that generic objects with well-defined closed boundaries share surprisingly strong correlation when looking at the norm of the gradient
resizing of their corresponding image windows to small fixed size (e.g. 8x8).
use the norm of the gradients as a simple 64D feature(NG feature)
Use cascaded SVM framework for learning objectness measure

7. 2. Methodology
＊we scan over a predefined quantized window sizes (scales and aspect ratios)
target window sizes {(Wo,Ho)}
Sl: filter score
i:size
gl: NG feature
(x,y): position of a window
l: location
＊we select a small set of proposals from each size i by Using non-maximal suppression (NMS)

8. 2. Methodology 2.1 Normed gradients (NG) and objectness
＊Maybe some sizes (e.g. 10 x 500) are less likely than others to contain an object instance (e.g.100 x 100)
2.1 Normed gradients (NG) and objectness
coefficient and a bias terms for each quantised size i
＊Objects are stand-alone things with well-defined closed boundaries and centers [3, 26, 32].
1.Firstly we resizing of their corresponding image windows to small fixed size (e.g. 8x8).
2. The resized normed gradients maps are defined as a 64D normed gradients (NG) feature of its corresponding window.

9. 2. Methodology ＊NG feature has several advantages
1.NG features are insensitive to change of translation, scale and aspect ratio, which will be very useful for detecting objects of arbitrary categories
2.NG feature makes it very efficient to be calculated and verified

10. 2. Methodology 2.2 Learning objectness measurement with NG
＊Two stages cascaded SVM [57].
ground truth object windows
Pos
Stage I. We learn a single model w for (1) using linear SVM
random sampled background windows
Neg
Stage II. To learn vi and ti in (3) using a linear SVM
we evaluate (1) at size i for training images and use the selected (NMS) proposals as training samples, their filter scores as 1D features, and check their labeling using training image annotations

11. 2. Methodology NG->BING 2.3 Binarized normed gradients (BING)
＊To use advantages of model binary approximation [28, 59]
Nw : the number of basis vectors
linear model
:basis vector
: Corresponding coefficient

12. 2. Methodology

13. 2. Methodology
＊How to binarize and calculate our NG features efficiently
We approximate the normed gradient values (each saved as a BYTE value) using the top Ng
binary bits of the BYTE values
64D NG feature gl can be approximated by Ng binarized normed gradients (BING) features
E.g. Decimal: 210 Binary: Top Ng=4 bits: 1101
210 ≈
= 1∗28−1+1∗28−2+0∗28−3+1∗28−4

14. 2. Methodology
＊First, a BING feature bx,y and its last row rx,y could be saved in a single INT64 and a BYTE variables
＊Second, adjacent BING features and their rows have a simple cumulative relation
the operator BITWISE SHIFT shifts rx-1,y by one bit, automatically through the bit which does not
belong to rx,y, and makes room to insert the new bit bx,y using the BITWISE OR operator.
Similarly BITWISE SHIFT shifts bx,y-1 by 8 bits automatically through the bits which do not belong to bx,y, and makes room to insert rx,y

15. 2. Methodology

16. 3. Experimental Evaluation
․Data set :VOC2007
Proposal quality comparisons
Generalize ability test
․evaluation metric : DR-#WIN
proposal quality
generalize ability
efficiency

17. 3. Experimental Evaluation
Computational time

18. 3. Experimental Evaluation

19. 3. Experimental Evaluation

20. 4. Conclusion and Future Work
․Limitations
For some object categories, a bounding box might not localize the object instances as accurately as a segmentation region
(e.g. a snake, wires, etc.)
․We present a surprisingly simple, fast, and high quality objectness measure by using 8X8 BING features
․Only needs a few atomic (i.e. ADD, BITWISE, etc.) operations
․The binary operations and memory efficiency make our method suitable to run on low power devices
․It suitable for realtime multi-category object detection applications and large scale image collections