Words & Pictures

Words & Pictures

Clustering and Bag of Words Representations

Many slides adapted from Svetlana Lazebnik, Fei-Fei Li, Rob Fergus, and Antonio Torralba

Announcements

• HW1 due Thurs, Sept 27 @ 12pm– By email to [email protected]. No need to

include shopping image set.– Write-up can be webpage or pdf.

mailto:[email protected]

Document Vectors

· Represent document as a “bag of words”

Origin: Bag-of-words models• Orderless document representation: frequencies

of words from a dictionary Salton & McGill (1983)

Origin: Bag-of-words models

US Presidential Speeches Tag Cloudhttp://chir.ag/phernalia/preztags/

• Orderless document representation: frequencies of words from a dictionary Salton & McGill (1983)

Bag-of-features models

Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba

Bags of features for image classification

1. Extract features

1. Extract features2. Learn “visual vocabulary”


1. Extract features2. Learn “visual vocabulary”3. Quantize features using visual vocabulary


1. Extract features2. Learn “visual vocabulary”3. Quantize features using visual vocabulary 4. Represent images by frequencies of

“visual words”


• Regular grid– Vogel & Schiele, 2003– Fei-Fei & Perona, 2005

1. Feature extraction


• Interest point detector– Csurka et al. 2004– Fei-Fei & Perona, 2005– Sivic et al. 2005



• Interest point detector– Csurka et al. 2004– Fei-Fei & Perona, 2005– Sivic et al. 2005

• Other methods– Random sampling (Vidal-Naquet & Ullman, 2002)– Segmentation-based patches (Barnard et al. 2003)


…


2. Learning the visual vocabulary

…


Clustering

…

Slide credit: Josef Sivic


Clustering

…


Visual vocabulary

Clustering

– The assignment of objects into groups (called clusters) so that objects from the same cluster are more similar to each other than objects from different clusters.

– Often similarity is assessed according to a distance measure.

– Clustering is a common technique for statistical data analysis, which is used in many fields, including machine learning, data mining, pattern recognition, image analysis and bioinformatics.

Any of the similarity metrics we talked about before (SSD, angle between vectors)

Feature Clustering

Clustering is the process of grouping a set offeatures into clusters of similar features.

Features within a cluster should be similar.

Features from different clusters should bedissimilar.

source: Dan Klein

K-means clustering

• Want to minimize sum of squared Euclidean distances between points xi and their nearest cluster centers mk

k

ki

ki mxMXDcluster

clusterinpoint

2)(),(

source: Svetlana Lazebnik

source: Dan Klein

Source: Hinrich Schutze

Hierarchical clustering strategies

• Agglomerative clustering• Start with each point in a separate cluster• At each iteration, merge two of the “closest” clusters

• Divisive clustering• Start with all points grouped into a single cluster• At each iteration, split the “largest” cluster

source: Svetlana Lazebnik

source: Dan Klein

Divisive Clustering

• Top-down (instead of bottom-up as in Agglomerative Clustering)

• Start with all docs in one big cluster• Then recursively split clusters• Eventually each node forms a cluster on its

own.


Flat or hierarchical clustering?

• For high efficiency, use flat clustering (e.g. k means)

• For deterministic results: hierarchical clustering• When a hierarchical structure is desired:

hierarchical algorithm• Hierarchical clustering can also be applied if K

cannot be predetermined (can start without knowing K)



Clustering

…



Clustering

…


Visual vocabulary

From clustering to vector quantization• Clustering is a common method for learning a visual

vocabulary or codebook– Unsupervised learning process– Each cluster center produced by k-means becomes a codebook

entry– Codebook can be learned on separate training set– Provided the training set is sufficiently representative, the

codebook will be “universal”

• The codebook is used for quantizing features– A vector quantizer takes a feature vector and maps it to the index

of the nearest entry in the codebook– Codebook = visual vocabulary– Codebook entry = visual word

Example visual vocabulary

Fei-Fei et al. 2005

Visual vocabularies: Issues

• How to choose vocabulary size?– Too small: visual words not

representative of all patches– Too large: quantization artifacts,

overfitting

• Computational efficiency– Vocabulary trees

(Nister & Stewenius, 2006)

3. Image representation

…..

freq

uenc

y

codewords

Image classification (next)

• Given the bag-of-features representations of images from different classes, how do we learn a model for distinguishing them?

Clustering in Action

President George W. Bush makes a statement in the Rose Garden while Secretary of Defense Donald Rumsfeld looks on, July 23, 2003. Rumsfeld said the United States would release graphic photographs of the dead sons of Saddam Hussein to prove they were killed by American troops. Photo by Larry Downing/Reuters

Names and Faces

Who’s in the picture?T.L. Berg, A.C. Berg, J. Edwards, D.A. Forsyth

Intuition

George Bush

500k News Corpora

Producer and director Bruce Paltrow has died at the age of 58 in Rome, Italy, the U.S. Consulate said on October 3, 2002. Paltrow had suffered from throat cancer for several years, but the cause of his death was not immediately known. He is seen with his daughter actress Gwyneth Paltrow after the Academy Awards in Los Angles in March 21, 1999 file photo. (Fred Prouser/Reuters)

Actress Winona Ryder (news) reacts to remarks by prosecutor Ann Rundle during the sentencing hearing in her felony shoplifting case Friday, Dec. 6, 2002 at the Beverly Hills, Calif., courthouse. At right is Ryder's attorney Mark Geragos. Ryder was sentenced to three years of probation and was ordered to perform 480 hours of community service. (APPhoto/Steve Grayson, POOL)


Name & Face Extraction

Detected Faces


Name & Face Extraction

Detected Names: President George W. Bush, Defense Donald Rumsfeld, Saddam Hussein.

Detected Faces

Each name in the dataset is a potential cluster. Want to simultaneously:1.) Learn image model for each person.

2.) Learn depiction model across names.

Achieve both of these by considering a big assignment (clustering) problem.

Goal

Assignment Problem

Language indicates Depiction


Cues - POS tags before and after name, location in caption, distance to closest: ( ) (L) (C) (R) left right center shown pictured above

P(Depicted | Context)

Yes/No multiple independent cues

1.) Update assignments

2.) Update: appearance model for each person. language model of depiction across

names.

Iterate 1-2

Method

Results

British director Sam Mendes and his partner actress Kate Winslet arrive at the London premiere of 'The Road to Perdition', September 18, 2002. The films stars Tom Hanks as a Chicago hit man who has a separate family life and co-stars Paul Newman and Jude Law. REUTERS/Dan Chung

World number one Lleyton Hewitt of Australia hits a return to Nicolas Massu of Chile at the Japan Open tennis championships in Tokyo October 3, 2002. REUTERS/Eriko Sugita

US President George W. Bush (L) makes remarks while Secretary of State Colin Powell (R) listens before signing the US Leadership Against HIV /AIDS , Tuberculosis and Malaria Act of 2003 at the Department of State in Washington, DC. The five-year plan is designed to help prevent and treat AIDS, especially in more than a dozen African and Caribbean nations(AFP/Luke Frazza)

German supermodel Claudia Schiffer gave birth to a baby boy by Caesarian section January 30, 2003, her spokeswoman said. The baby is the first child for both Schiffer, 32, and her husband, British film producer Matthew Vaughn, who was at her side for the birth. Schiffer is seen on the German television show 'Bet It...?!' ('Wetten Dass...?!') in Braunschweig, on January 26, 2002. (Alexandra Winkler/Reuters)

Results

Results

Without – CEO SummitWith – Martha Stewart

Without – James BondWith – Pierce Brosnan

Without – Dick CheneyWith – George W. Bush

Model Accuracy of labelingVision model, No Lang model

67%

Vision model + Lang model 78%

Face Dictionary

http://tamaraberg.com/faces/faceDict/NIPSdict/index.html

http://tamaraberg.com/faces/faceDict/NIPSdict/index.html

Results - Depiction

Classifier % correctBaseline (all pictured) 67%Learned Lang Model 86%

IN - pictured, OUT - not pictured

Words & Pictures

Documents

Transcript of Words & Pictures