SLIDE 1
Contents
- Introduction
- Related works
- Main approaches
- Results
- Conclusion
Particular Object Retrieval with Integral Max-pooling of CNN - - PowerPoint PPT Presentation
Particular Object Retrieval with Integral Max-pooling of CNN - - PowerPoint PPT Presentation
Particular Object Retrieval with Integral Max-pooling of CNN Activations Tolias et al. ICLR 2016 Presented by Jaehyeong Cho Contents Introduction Related works Main approaches Results Conclusion Introduction How to find
SLIDE 2
SLIDE 3
Introduction
- How to find similar images?
- Convert an image into a single feature (e.g. BoW, VLAD, CNN)
- Measure the similarity between features
=> Quality of features highly affects the retrieval results
- Are all parts of an image equally representative?
- No, it is better to focus on important regions only
- Main contribution
- Encodes several image regions into single compact feature
- Localizes matching objects
SLIDE 4
Related works
- Retrieval methods considering spatial information
- Babenko and Lempitsky, Aggregating Deep Convolutional Features
for Image Retrieval, ICCV 2015
- Aggregates multiple convolutional features from various position in
an image
- Gives higher weights for the features near the center
SLIDE 5
Related works
- Retrieval methods considering spatial information
- Kalantidis et al., Cross-dimensional Weighting for Aggregated Deep
Convolutional Features, ECCV workshop 2016
- Gives different weights according to the channel and location
SLIDE 6
Related works
- Retrieval methods considering spatial information
- Xie et al., Image Classification and Retrieval are ONE, ICMR 2015
- Extract CNN features from object regions
- Represent an image with multiple features
SLIDE 7
Main approaches
- Maximum activations of convolutions (MAC)
- Proposed by Azizpour et al., 2014
- CNN activations for an image I
- W × H × K
- Utilizes only maximum activations from each channel
- Enables to capture representative regions
- But lacks location information
SLIDE 8
Main approaches
- Regional maximum activations of convolutions (R-MAC)
- Extract MAC from multiple regions
=> Encodes the location information
- Makes a single feature by summation
SLIDE 9
Main approaches
- Object localization
- q : MAC feature from the query object (blue)
- Find the region that maximize the similarity
- Fast computation of
fR
T is required
SLIDE 10
Main approaches
- Object localization
- Approximation of
fR
T
- Localization result helps re-ranking
SLIDE 11
Results
- Comparison of retrieval accuracy
- without post-processing
SLIDE 12
Results
- Comparison of retrieval accuracy
- with post-processing
SLIDE 13
Results
- Re-ranking with object localization
SLIDE 14
Conclusion
- Generated improved feature vector by encoding location
information into the feature
- Approximated max-pooling process for fast computation
- Localized the target object and effectively used it for re-ranking
SLIDE 15
References
- Babenko, Artem, and Victor Lempitsky. "Aggregating local deep features for image
retrieval." Proceedings of the IEEE International Conference on Computer Vision. 2015.
- Kalantidis, Yannis, Clayton Mellina, and Simon Osindero. "Cross-dimensional weighting
for aggregated deep convolutional features." arXiv preprint arXiv:1512.04065 (2015).
- Xie, Lingxi, et al. "Image classification and retrieval are one." Proceedings of the 5th
ACM on International Conference on Multimedia Retrieval. ACM, 2015.
- Azizpour, Hossein, et al. "From generic to specific deep representations for visual
recognition." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2015.