Warning

# 2014 XEP33SAM -- Understan​ding State of the Art Methods, Algorithms​, and Implementa​tions

Meeting time: Thursday 16:15 pm G102A

## First meeting 20/3 2014

#### Paper

Marius Muja and David G. Lowe: “Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration”, in International Conference on Computer Vision Theory and Applications (VISAPP'09), 2009 PDF software page

• Implement approximate k-means algorithm, use approximate NN instead of exact NN
• Construct k-NN graph: a directed graph, vertex is a feature vector, from each vertex there are k edges to k nearest data vectors

Oxford 5k dataset: image thumbnails, descriptors (128 D vectors, single precision, stored one by one), and corresponing image names (one name per line, i-th name corresponds to i-th descriptors).

The following lines will read the descriptors and the image names in MATLAB:

fid = fopen('imagedesc.dat', 'r');
fclose(fid);

SIFT dataset: 2M SIFT descriptors are available here. The descriptors are 128D unsigned byte precision, the following Matlab lines will read the descriptors:

fid = fopen('SIFT.dat', 'r');
fclose(fid);

Use the SIFT dataset for the approximate k-means. Use 32k cluster centers. Compare three different assignments to the nearest cluster (kd-forest, k-means tree, exact assignmet). For all three cases, start from identical inicialization. Compare the final results (up to say 30 iterations) in terms of sum of squared distances, that is Σ (X - f(X))^2, where f(X) is the assigned cluster center.

Looking forward to results on your own data too.

## Second meeting TBA

#### Paper

Herve Jegou, Matthijs Douze, Cordelia Schmid: “Product quantization for nearest neighbor search”, PAMI 2011. PDF software page

(Do not get confused by the text on the page. The mex version is in the package.)

Oxford 105k dataset: image thumbnails were distributed during the previous meeting,descriptors (128 D vectors, single precision, stored one by one), and corresponing image names (one name per line, i-th name corresponds to i-th descriptors, Oxford 5k image names are given without a directory, remaining filenames contain a directory corresponding to the distributed directory structure).

• For each image find k-NN, visually verify the quality - script that for a selected image shows the k neighbours, etc.
• Compare the quality and running time of product quantization and FLANN. Select 1000 images at random and find exact k-NN, for each of the algorithms compute an estimate of its precision.

## Third meeting 6/5/2013 (Tuesday! 15:00 - to be confirmed)

Carsten Rother, Vladimir Kolmogorov, and Andrew Blake: “GrabCut” - Interactive Foreground Extraction using Iterated Graph Cuts, SIGGRAPH 2004. PDF, project page

Implement GrabCut using the graph cut (max flow) algorithm. Use the code by Vladimir Kolmogorov, considered the best current implementation. There is a number of wrappers, this one was pointed out by Kostia (he has experience compiling it).

Use some standard images (from the project page) to verify that you are doing the right thing.

## Fourth meeting 28/5/2014

#### Paper

The paper / chapter that will be discussed will be posted soon.

Yuri Boykov, Olga Veksler and Ramin Zabih: “Fast Approximate Energy Minimization via Graph Cuts”, PAMI 2001. PDF, (further reading: KZ-PAMI04 and SAUAI11) software page