Objectness measure V2.2
What is objectness?
The objectness measure acts as a class-generic object detector. It quantifies how likely it is for an image window to contain an object of any class, such as cars and dogs, as opposed to backgrounds, such as grass and water. We release here software for computing objectness [1,2] and sampling any desired number of windows from an image according to their probability of containing an object.
For applications, we recommend to sample about 1000 windows, which ensures covering most objects even in very difficult images (e.g. with small objects and lots of clutter). However, in images of normal difficulty 100 windows are sufficient (e.g. images downloaded from image search engines).
From version V 1.5 we include a new window sampling strategy (NMS) which leads to higher detection rates. On the highly challenging PASCAL VOC 2007 dataset , the top 1000 sampled windows now cover 91% of all objects , as opposed to about 70% in previous versions using multinomial sampling .
In addition to the source code, we also release sampled windows for every image from PASCAL VOC 2007 , for both the new NMS sampling strategy and for the older multinomial sampling. These ready-to-use windows hopefully will facilitate applications on this dataset.
How fast is it?
Objectness is computationally efficient. On a mid-range PC, it takes less than 3 seconds to compute the objectness measure and to sample 1000 windows, for an image of size 350 x 500.
Applications of objectnessObjectness is intended as a low-level preprocessing stage, to propose a small number of windows likely to cover all objects in the image. It has been used in several applications so far:
+ weakly supervised localization [4,5,9,12,15,16,31,32,33]
+ weakly supervised segmentation of a single object class  and of multiple classes 
+ unsupervised object discovery [8,34]
+ content-aware image resizing [10,11]
+ speeding up class-specific detectors [1,2,29]
+ reducing the false-positive rates of class-specific detectors [1,2]
+ object tracking in video [17,21,22,35]
+ large-scale knowledge transfer [18,19,20]
+ co-segmentation [26,27,40]
+ video co-segmentation 
+ image quality assessment 
+ image difficulty assessment 
+ building block or inspiration for other class generic detectors [13,23,24,25,30,37]
+ salient object detection [14, 42]
+ background detection 
+ improving spatial support for object detection measurements 
+ improving accuracy of object localization at superpixel level 
For each of image we show the windows best covering the objects annotated in the PASCAL VOC 2007 (our of 1000 windows sampled with NMS). We mark in yellow windows correctly covering ground-truth objects (cyan); if there is more than one correct window, the best one is shown.
For each image we show its pixelwise objectness map. This is obtained by sampling 1000 windows using the NMS sampling procedure and accumulating them. We do this
by computing for each image pixel the sum of the objectness scores for the sampled windows containing it. Objectness maps provide meaningful distributions over the object
locations, demonstrating that it reduces their uncertainty.
|Source code (Matlab/C)||Souce code for objectness measure||21 MB|
|README.txt||Description of content||10 kB|
|LICENSE||Software license||1 kB|
|PASCAL VOC 2007 windows using NMS sampling||1000 windows sampled using the NMS strategy for each image in PASCAL VOC 2007 (recommended)||86 MB|
|PASCAL VOC 2007 windows using multinomial sampling||10000 windows sampled using the multinomial strategy for each image in PASCAL VOC 2007||576 MB|
New in V 2.2
+ minor speedups thanks to avoiding intermediate load/save steps; this software now no longer needs the external tool 'convert' to be installed on your machine
New in V 2.1
+ sampling windows for small sized images doesn't crash anymore
New in V 2.0
+ mex file to fastly compute the superpixel segmentation added
+ function to compute the objectness heat map of an image added
New in V 1.5
+ NMS sampling procedure added
New in V 1.01
+ windows with width or height = 1 pixel are not anymore considered
 Alexe, B., Deselares, T. and Ferrari, V.
What is an object?
 Alexe, B., Deselares, T. and Ferrari, V.
Measuring the objectness of image windows
 Everingham, M., Van Gool, L., Williams, C., Winn, J., and Zisermann, A.
The PASCAL Visual Object Classes Challenge 2007
 Deselares, T., Alexe, B. and Ferrari, V.
Localizing objects while learning thier appearance
 Khan, I., Roth, P. M. and Bischof, H.
Learning Object Detectors from Weakly-Labeled Internet Images
OAGM Workshop 2011.
 Alexe, B., Deselaers, T. and Ferrari, V.
ClassCut for unsupervised class segmentation
 Vezhnevets, A., Ferrari, V. and Buhmann, J.
Weakly supervised semantic segmentation with a multi-image model
 Lee, Y. J. and Grauman, K.
Learning the easy things first: Self-paced visual category discovery
 Prest, A., Schmid, C. and Ferrari, V.
Weakly supervised learning of interactions between humans and objects
 Sun, J., and Ling, H.
Scale and Object Aware Image Retargeting for Thumbnail Browsing
 Bao, X., Narayan, T., Sani, A. A., Richter, W., Choudhury, R. R., Zhong, L. and Satyanarayanan, M.
The Case for Context-Aware Compression
ACM Hotmobile 2011.
 Siva, P. and Xiang, T.
Weakly Supervised Object Detector Learning with Model Drift Detection
 Rahtu, E., Kannala, J. and Blaschko, M.
Learning a Category Independent Object Detection Cascade
 Chang, K. Y., Liu, T. L., Chen, H. T., and Lai, S. H.
Fusing Generic Objectness and Visual Saliency for Salient Oject Detection
 Siva, P., Russell C., and Xing, T.
In Defense of Negative Mining for Annotating Weakly Labelled Data
 Sener, F., Bas, C., and Ikizler-Cinbis, N.
On Recognizing Action in Still Images via Multiple Features
1st Workshop on Action Recognition and Pose Estimation in Still Images, ECCV 2012.
 Stadler, S., Grabner, H., and Van Gool, L.
Dynamic Objectness for Adaptive Tracking
 Guillaumin, M., and Ferrari, V.
Large-scale knowledge transfer for object localization in ImageNet
 Kuettel, D., and Ferrari, V.
Figure-ground segmentation by transferring window masks
 Kuettel, D., Guillaumin, M., and Ferrari, V.
Segmentation Propagation in ImageNet
 Spampinato, C., and Palazzo, S.
Enhancing object detection performance by integrating motion objectness and perceptual organization
 Lu, Z., and Grauman, K.
Story-Driven Summarization for Egocentric Video
 Blaschko, M., Kannala, J., and Rahtu, E.
Non Maximal Suppression in Cascade Ranking Models
 Siva, P., Russell, C., Xiang, T., and Agapito, L.
Looking Beyond the Image: Unsupervised Learning for Object Saliency and Detection
 Ristin, M., Gall, J., and Van Gool, L.
Local Context Priors for Object Proposal Generation
 Rubio, J., Serrat, J., Lopez, A., and Paragios, N.
Unsupervised co-segmentation through region matching
 Meng, F., Li, H., Liu, G., and Ngan, K. N.
Object Co-segmentation based on Shortest Path Algorithm and Saliency Model
 Mai, L., Le, H., Niu, Y., and Liu, F.
Rule of Thirds Detection from Photograph
 Saenko, K., Karayev, S., Jia, Y., Shyr, A., Janoch, A., Long, J., Fritz, M., and Dareell, T.
Practical 3-D Object Detection Using Category and Instance-level Appearance Models
 Gao, Y., Zhang, J., Zhang, L., and Hu, Y.
Finding objects at indoor environment combined with depth information
 Shapovalova, N., Vahdat, A., Cannons, K., Lan, T., and Mori, G.
Similarity Constrained Latent Support Vector Machine: An Application to Weakly Supervised Action Classification
 Deselaers, T., Alexe, B., and Ferrari, V.
Weakly Supervised Localization and Learning with Generic Knowledge
 Prest, A., Leistner, C., Civera, J., Schmid, C., and Ferrari, V.
Learning Object Class Detectors from Weakly Supervised Annotated Video
 Bodesheim, P.
Spectral Clustering of ROIs for Object Discovery
 Loo, W. and Kim, T.K.
Generic Object Crowd Tracking by Multi-Task Learning
 Russakovsky, O., Deng, J., Huang, Z., Berg, A. and Fei-Fei, L.
Detecting avocados to zucchinis: what have we done, and where are we going?
 Jia, Y. and Han, M.
Category-Independent Object-level Saliency Detection
 Cinbis, R. G., Verbeek, J. and Schmid, C.
Segmentation Driven Object Detection with Fisher Vectors
 Rubio, J. C., Serrat, J. and Lopez, A.
 Meng, F., Li, H., Ngan, K. N., Zeng, L. and Wu, Q.
Feature Adaptive Co-segmentation by Complexity Awareness
 Karaoglu, S., Van Gemert, J. C. and Gevers, T.
Con-Text: Text Detection Using Background Connectivity for Fine-Grained Object Classification
 Jiang, P., Ling, H., Yu, J. and Peng, J.
Salient Region Detection by UFO: Uniqueness, Focusness and Objectness
 Li, L., Feng, W., Wan, L., and Zhang, J.
Maximum Cohesive Grid of Superpixels for Fast Object Localization
This work is funded by the Swiss National Science Foundation SNSF