Computational Vision at Caltech

Categorie: Color/Hyperspectral Images Publicat: 25 Mai 2015

Scris de Alex Accesări: 909

Description

Pictures of objects belonging to 101 categories. About 40 to 800 images per category. Most categories have about 50 images. Collected in September 2003 by Fei-Fei Li, Marco Andreetto, and Marc 'Aurelio Ranzato. The size of each image is roughly 300 x 200 pixels.
We have carefully clicked outlines of each object in these pictures, these are included under the 'Annotations.tar'. There is also a matlab script to view the annotaitons, 'show_annotations.m'.

How to use the dataset

If you are using the Caltech 101 dataset for testing your recognition algorithm you should try and make your results comparable to the results of others. We suggest training and testing on fixed number of pictures and repeating the experiment with different random selections of pictures in order to obtain error bars. Popular number of training images: 1, 3, 5, 10, 15, 20, 30. Popular numbers of testing images: 20, 30. See also the discussion below.
When you report your results please keep track of which images you used and which were misclassified. We will soon publish a more detailed experimental protocol that allows you to report those details. See the Discussion section for more details.

Download

Collection of pictures: 101_ObjectCategories.tar.gz (131Mbytes)

Outlines of the objects in the pictures: [1] Annotations.tar [2] show_annotation.m

Literature

Papers reporting experiments on Caltech 101 images:

1. Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. L. Fei-Fei, R. Fergus, and P. Perona. CVPR 2004, Workshop on Generative-Model Based Vision. 2004

2. Shape Matching and Object Recognition using Low Distortion Correspondence. Alexander C. Berg, Tamara L. Berg, Jitendra Malik . CVPR 2005

3. The Pyramid Match Kernel:Discriminative Classification with Sets of Image Features. K. Grauman and T. Darrell. International Conference on Computer Vision (ICCV), 2005.

K. Grauman and T. Darrell. Pyramid Match Kernels: Discriminative Classification with Sets of Image Features. MIT-CSAIL-TR-2006-020. March 18, 2006. ** Report demonstrates much stronger performance on the 101 using dense sampling as features. Also, in this report, results are normalized by the number of images in each class to make results comprable to other published results. **

4. Combining Generative Models and Fisher Kernels for Object Class Recognition Holub, AD. Welling, M. Perona, P. International Conference on Computer Vision (ICCV), 2005.

Exploiting Unlabelled Data for Hybrid Object Classification. Holub, AD. Welling, M. Perona, P. NIPS 2005 Workshop in Inter-Class Transfer.

5. Object Recognition with Features Inspired by Visual Cortex. T. Serre, L. Wolf and T. Poggio. Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), IEEE Computer Society Press, San Diego, June 2005.

6. SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition. Hao Zhang, Alex Berg, Michael Maire, Jitendra Malik. CVPR, 2006.

Link to web-page describing results.

7. Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories. Svetlana Lazebnik, Cordelia Schmid, and Jean Ponce. CVPR, 2006 (accepted).

8. Empirical study of multi-scale filter banks for object categorization, M.J. Marín-Jiménez, and N. Pérez de la Blanca. December 2005. Tech Report.

9. Multiclass Object Recognition with Sparse, Localized Features, Jim Mutch and David G. Lowe. , pg. 11-18, CVPR 2006, IEEE Computer Society Press, New York, June 2006.

10. Using Dependant Regions or Object Categorization in a Generative Framework, G. Wang, Y. Zhang, and L. Fei-Fei. IEEE Comp. Vis. Patt. Recog. 2006