authors : antonio torralba, kevin p. murphy, william t. freeman, and mark a. rubin
DESCRIPTION
An opposition to: Context-Based Vision System for Place and Object Recognition Contextual Models for Object Detection Using BRFs. Authors : Antonio Torralba, Kevin P. Murphy, William T. Freeman, and Mark A. Rubin Opponent : Carlos Vallespi. Paper claims. - PowerPoint PPT PresentationTRANSCRIPT
An opposition to:
Context-Based Vision System for Place and Object Recognition Contextual Models for Object Detection Using BRFs
Authors: Antonio Torralba, Kevin P. Murphy, William T. Freeman, and Mark A. Rubin
Opponent: Carlos Vallespi
Paper claims Claims to recognize 63 different locations. Claims to categorize new environments Claims to help object recognition by
suggesting presence and location.
Place recognition
Temporal information is available. HMM will help a lot to the classifier.
Only 2-3 choices are possible at a time, knowing the current state.
Is the classifier really doing anything?
Is the classifier really doing anything?
Simple place recognition with SIFT
Database
Simple place recognition with SIFT
Test DB
Comparing with SIFT
74 matches
Comparing with SIFT
Some correct matches
Comparing with SIFT
Correct no matches
Comparing with SIFT No incorrect mismatches Just one weak match (22 matches):
Provided 9 locations and 100% accuracy in the test set.
Scene categorization This paper claims that they are able to categorize 17 unseen scenarios. We have seen other methods in the past for scene categorization that also
worked well (with up to 13 classes): Bag-of-words approaches (using textons, for instance). Histogram-based approaches. Torralba’s paper (using image frequencies).
They use an average of local features over the image with a sliding window.
In fact, this is just a sort of histogram approach (nothing new). DB does not seem very generic. They do not compare with other
methods. It performs poorly, except for the exception of the HMM:
Object presence and location Their own images speak for themselves ;)
???
A filecabinet is expected to be seen in almost the entire image.
Most of the objects that are highly expected to be found, do not show up.
Object presence and location Their own images speak for themselves ;)
Except for the case of the building (which I am sure I could get something similar by averaging all the bounding boxes of buildings), all others are wrong… even the sky.
Conclusions Place recognition:
It seems to be an easy problem, that can be solved by simpler methods without temporal information.
An HMM alone could have done similar work. Scene categorization:
Suspicious DB Only works because of the temporal information.
Object presence and location: Just does not work.