Tag Archives: research notes

Selfai: A Method for Understanding Beauty in Selfies

Selfies are everywhere. With different fun masks, poses and filters,  it goes crazy.  When we coincide with any of these selfies, we automatically give an intuitive score regarding the quality and beauty of the selfie. However, it is not really possible to describe what makes a beautiful selfie. There are some obvious attributes but they are not fully prescribed.

With the folks at 8bit.ai, we decided to develop a system which analyzes selfie images and scores them in accordance to its quality and beauty.  The idea was to see whether it is possible to mimic that bizarre perceptual understanding of human with the recent advancements of AI. And if it is, then let's make a mobile application and let people use it for whatever purpose. Spoiler alert! We already developed Selfai app available on iOS and Android and we have one instagram bot @selfai_robot. You can check before reading.

 

Selfai - available on iOS and Android
Selfai - available on iOS and Android

 

Continue reading Selfai: A Method for Understanding Beauty in Selfies

ImageNet winners after 2012

  • 2012
    • 0.15 - Supervision (AlexNet) - ~ 60954656 params
    • 0.26 - ISI (ensemble of features)
    • 0.27 - LEAR (Fisher Vectors)
  • 2013
    • 0.117 - Clarifai (paper)
    • 0.129 - NUS (very parametric but interesting method based on test and train data affinities)
    • 0.135 - ZF (same paper)
  • 2014
    • 0.06 - GoogLeNet (Inception Modules) -  ~ 11176896 params
    • 0.07 - VGGnet (Go deeper and deeper)
    • 0.08 - SPPnet  (A retrospective addition from early vision)

Bits and Missings for NNs

  • Adversarial instances and robust models
    • Generative Adversarial Network http://arxiv.org/abs/1406.2661 -  Train classifier net as oppose to another net creating possible adversarial instances as the training evolves.
    • Apply genetic algorithms per N training iteration of net and create some adversarial instances.
    • Apply fast gradient approach to image pixels to generate intruding images.
    • Goodfellow states that DAE or CAE are not full solutions to this problem. (verify why ? )
  • Blind training of nets
    • We train huge networks in a very brute force fashion. What I mean is, we are using larger and larger models since we do not know how to learn concise and effective models. Instead we rely on redundancy and expect to have at least some units are receptive to discriminating features.
  • Optimization (as always)
    • It seems inefficient to me to use back-propagation after all these work in the field. Another interesting fact, all the effort in the research community goes to find some new tricks that ease back-propagation flaws. I thing we should replace back-propagation all together instead of daily fleeting solutions.
    • Still use SGD ? Still ?
  • Sparsity ?
    • After a year of hot discussion for sparse representations and it is similarity to human brain activity, it seems like it's been shelved. I still believe, sparsity is very important part of good data representations. It should be integrated to state of art learning models, not only AutoEncoders.

DISCLAIMER:  If you are reading this, this is only captain's note and intended to my own research make up.  So many missing references and novice arguments.