Marius Leordeanu, Martial Hebert, Raul Sukthankar CVPR07 CVPR 07 - - PowerPoint PPT Presentation

marius leordeanu martial hebert raul sukthankar cvpr 07
SMART_READER_LITE
LIVE PREVIEW

Marius Leordeanu, Martial Hebert, Raul Sukthankar CVPR07 CVPR 07 - - PowerPoint PPT Presentation

Marius Leordeanu, Martial Hebert, Raul Sukthankar CVPR07 CVPR 07 Presented by Weina Ge Problem Problem Image categorization and localization , given negative images and weakly labeled positive images Contributions Learning


slide-1
SLIDE 1

Marius Leordeanu, Martial Hebert, Raul Sukthankar CVPR’07 CVPR 07

Presented by Weina Ge

slide-2
SLIDE 2

Problem Problem

Image categorization and localization, given negative

images and weakly labeled positive images

Contributions

L i bj t/ t d l i kl i d

Learning object/category models in a weakly‐supervised

fashion

▪ Object models: cliques of fully‐interconnected parts

shape

▪ Pairwise geometric relationship

Simple features

▪ Sparse points and their normals ▪ Sparse points and their normals

slide-3
SLIDE 3
slide-4
SLIDE 4

Features Localization as feature matching

g

Matching score: Quadratic assignment problem (QAP): Quadratic assignment problem (QAP):

▪ Solved by spectral matching algorithm with one‐to‐one mapping constraints

slide-5
SLIDE 5

h ll b h

There will be an assignment in matching no matter

what, so we need to do recognition

Model the posterior

Model the posterior:

▪ C = 1 if the object is present at location x*; otherwise C=0 ▪ D – data

Posterior is a function of

▪ quality of matching ▪ quality of matching ▪ quality of model parts: relevant to the particular category and

discriminative against the negative class

slide-6
SLIDE 6

Approximate the posterior by a logistic classifier

pp p y g

1: detected 0: absent

  • matching quality (pairwise potentials)

0 abse

  • model quality (relevance parameter )
  • sigmoid function

h h l h

  • squashes the relevance parameter to either 1 or 0
  • reduces the overfitting without an explicit regularization term
slide-7
SLIDE 7

d l

Model parameters

Model parts and their geometric relationships

=

Sensitivity to geometric deformations

= Learned independently of object parts and object class

Relevance parameter

Sequential gradient descent

Objective function

slide-8
SLIDE 8

Each model usually contains 40~100 parts

y p

slide-9
SLIDE 9

M i f t f diff t i i t

Merging features from different viewpoints

M d l t t tl b i dd d d d

Model parts are constantly being added and removed

slide-10
SLIDE 10

L i i l ifi d l h i h i i f

Logistic classifiers model the posterior that a given pair of

assignments is correct given the geometric deformation

Manually‐selected correspondences

8000 pairs of correct ones and 16000 pairs of wrong ones per database 3 databases: CALTECH 5 INRIA horses GRAZ 02 3 databases: CALTECH‐5, INRIA‐horses, GRAZ‐02

Experiments imply the space of geometric second‐order

d f i i l h dl f bj deformations is more or less the same regardless of object classes vs

slide-11
SLIDE 11
slide-12
SLIDE 12

PASCAL dataset (587 images)

PASCAL dataset (587 images)

“Ours” VS Winn et al. (different features)

geometric constraints VS appearance

geometric constraints VS appearance

slide-13
SLIDE 13

d

GRAZ datasets

“Ours” VS Opelt et al. (different feature selection criteria)

▪ performance of a group of features VS individual features ▪ performance of a group of features VS individual features

slide-14
SLIDE 14

l h

Clear theme

Proof shape is an important cue for recognition

Careful design of experiments

Every set of experiments serves a purpose

Every set of experiments serves a purpose