• It works in the opposite direction of the image classifier (CNN). • CNN transforms an image to a class label (list of probabilities). • DCGAN generates an image from random parameters. (0.01, 0.05, 0.91, 0.02, ...) deer dog cat human ... (0.01, 0.05, 0.91, 0.02, ...) CNN DCGAN Probabilities of each entry. What does these numbers mean? Random parameters
filters to extract various features from a single image. ▪ CNN applies multi-layered filters to a single image (to extract features of features?) ▪ An filtered image becomes smaller to drop off unnecessary details. Extracting vertical and horizontal edges using two filters.
Transposed-convolutional filters in DCGAN works in the opposite directions. Here's a good Illustration how they work. http://deeplearning.net/software/theano_versions/dev/tutorial/conv_arithmetic.html Convolution: (Up to) 3x3 blue pixels contribute to generate a single green pixel. Each of 3x3 blue pixels is multiplied by the corresponding filter value, and the results from different blue pixels are summed up to be a single green pixel. Transposed-convolution: A single green pixel contributes to generate (up to) blue 3x3 pixels. Each green pixel is multiplied by each of 3x3 filter values, and the results from different green pixels are summed up to be a single blue pixel. GIF Animation https://goo.gl/tAY4BL
two models simultaneously. • CNN: Classifying authentic and fake images. • "Authentic" images are provided as training data to CNN. • DCGAN: Trained to generate images classified as authentic by CNN. • By trying to fake CNN, DCGAN learns to generate images similar to the training data. CNN DCGAN Training data
becomes more wise and DCGAN becomes more crafty. CNN DCGAN Training data B Generated image A Random numbers P(A) : Probability that A is authentic. P(B) : Probability that B is authentic. Modify parameters to the direction where P(A) becomes large Modify parameters to the direction where P(A) becomes small and P(B) becomes large
▪ DCGAN : Generate a single 28x28 image from 64 parameters. • → 128 x (7x7) → 64 x (14x14) → 1 x (28x28) ▪ CNN : Calculate a probability that a single 28x28 image is authentic. • 1 x (28x28) → 64 x (14✕14) → 128 x (7x7) → Probability of authentic image ▪ Batch size : 32 • Modify filter parameters using 32 generated images and 32 MNIST images at a time.
parameter continuously, the shape of generated image changes continuously, too. We can achieve the morphing effect using this mechanism. ▪ Since the input parameter is a point in the 64 dimensional space, we can draw a straight line between two points. The end points represents images before and after morphing.
in the parameter space, we can even make a dancing image :) ▪ The sample image on this page is generated from the trajectory over a sphere (embedded in the 64 dimensional space.) GIF Animation https://goo.gl/zXL1bV