Regionlets for Generic Object Detection

Report
Regionlets for Generic
Object Detection
Xiaoyu Wang, Ming Yang, Shenghuo Zhu, and Yuanqing Lin
NEC Labs America, Inc.
Facebook, Inc.
ICCV 2013 oral paper
Presenter: Ming-Ming Cheng @ VGG reading group, 6/2/2014.
Generic object detection
Review: rigid vs. deformable
Rigid objects
Tackles local variations, hardly handle deformations
• Classical cascaded AdaBoost
• Deformable part models (DPM)
• Spatial pyramid matching (SPM) of BoW
Deformable objects
High deformation tolerance results in imprecise
localization or false positives for rigid objects
Can we mode both rigid and deformable objects in a
unified framework?
Review: parameter selection
• Deformable Part-based Model (DPM)
• Specify the number of deformable parts
• Spatial Pyramid Matching
• Specify the number of pyramids to build
Do we have to pre-define model parameters to
handle different degrees of deformation?
Review: multi scales/viewpoints
• DPM
• Resize an image to detect objects at a fixed scale
• Multiple models, each deals with one viewpoint
• Spatial Pyramid Matching
• No need to resize the image
• One model, a codebook is used to encode features
Can we learn a model that can be easily adapted to
arbitrary scales and viewpoints?
Review: sliding window vs. selective search
• Classical: sliding window
• Check hundreds of thousands (if not millions) of sliding windows.
• Resize image and detect objects at fixed scale
• Needs to use very efficient classifiers
• Recent: selective search
• Thousands of object-independent candidate regions
• [12PAMI] B. Alexe, T. Deselaers, and V. Ferrari, Measuring the objectness
of image window.
• [13IJCV] K. E. A. Van de Sande, J. R. R. Uijlings, T. Gevers, and A. W. M.
Smeulders, Selective search for object recognition
• [13PAMI] Ian Endres, and Derek Hoiem, Category-independent object
proposals with diverse ranking.
• [11ICCV] E. Rahtu, J. Kannala, and M. Blaschko. Learning a category
independent object detection cascade.
• [11CVPR] Z. Zhang, J. Warrell, and P. H. S. Torr. Proposal generation for
object detection using cascaded ranking SVMs. InCVPR, 2011
• Allowing strong classifier, needs to work with arbitrary window size
Motivation
• A flexible and general object-level representation with
• Hassle free deformation handling
• Arbitrary scales and aspect ratio handling
Detection framework
• Generate candidate detection bounding boxes
• Boosting classifier cascades
Regionlet: Definition
• Region (): feature extraction region
• Regionlet (1 , 2 , 3 ): A sub-region in a feature
extraction area whose position/resolution are relative
and normalized to a detection window
Bounding box
Region
Regionlets
Why regionlets?
Some part of the region may not
be informative or even distractive.
Why ‘regionlets’?
Regionlet: definition (cont.)
• Relative normalized position
Regionlet: Feature extraction
Regionlet
• Constructing the regions/regionlets pool
• Small region, fewer regionlets -> fine spatial layout
• Large region, more regionlets -> robust to deformation
• Use cascaded boosting learning to select the most
discriminative regionlets from a largely over-complete pool
Regionlet: Training
• Construct regionlets pool
• Enumerating all possible
regions is impractical and
not necessary.
• Propose a set of regionlets
with random positions (up
to 5) inside each region
with identical size.
Regionlet: Training
• Constructing the regions/regionlets poolLearning
Boosting cascades
• 16K region/regionlets candidates for each cascade
• Learning of each cascade stops when the error rate is
achieved (1% for positive, 37.5% for negative)
• Last cascade stops after collecting 5000 weak classifiers
• Result in 4-7 cascades
• 2-3 hours to finish training one category on a 8-core machine
Regionlets: Testing
• No image resizing
• Any scale, any aspect ratio
• Adapt the model size to the same size as the object
candidate bounding box
Experiments
• Datasets
• PASCAL VOC 2007, 2010
• 20 object categories
• ImageNet Large Scale Object Detection Dataset
• 200 object categories
• Investigated Features
•
•
•
•
HOG
LBP
Covariance
Deep Convolutional Neural Network (DCNN) feature (only for
the ImageNet challenge)
Experiments: PASCAL VOC
• Baselines
• DPM: excellent at detecting rigid objects. E.g. car, bus, etc.
• SS_SPM: for objects with significant global deformations.
• E.g. cat, cow sheep, etc.
• SPM outperforms DPM in airplane and TV. Due to very diverse
viewpoints or rich sub-categories.
• Objectness (use old version of DPM): selective search itself
dose not benefit detection tool much (0.6% improvement) in
terms of accuracy.
Experiments: PASCAL VOC
• Baselines:
• DPM
• SPM
• Objectness
• Regionlets
• Won 16 out of 20 categories
• ‘To our best knowledge, is the best performance in VOC07’
• Multiple regionlets consistently outperforms single regionlets
Experiments: PASCAL VOC
Experiments: ImageNet
Running speed
• 0.2 second per image using a single core if candidate
bounding boxes are given, real time(>30 frames per
second) using 8 cores 
• 2 seconds per image to generate candidate bounding
boxes 
• 2-3 hours to finish training one category on a 8-core
machine 
Conclusions
• A new object representation for object detection
• Non-local max-pooling of regionlets
• Relative normalized locations of regionlets
• Flexibility to incorporate various types of features
• A principled data-driven detection framework, effective
in handling deformation, multiple scales, multiple
viewpoints
• Superior performance with a fast running speed
Latest results
• Regionlets with Deep CNN feature (outside data)
Some really exciting parts
during the reading group will
be made public valuable after
CVPR 2014 results announced,
together with source code!
My thoughts towards a real-time system
• Current bottleneck is object proposal generation
• State of the art methods needs 2+ seconds to process one
image [IJCV13, PAMI12, PAMI13]
• Our recent results
Training on VOC: 20s
Testing speed: 300fps
Generic ability
My thoughts towards a real-time system
My thoughts towards a real-time system

similar documents