Séminaire IMAGE : « Patch and attention for image editing » (Nicolas Cherel)

Titre: « Patch and attention for image editing »

Résumé : We show through two different examples that patch-based methods remain relevant despite the widespread use of neural networks for many image editing tasks.
We first present a patch-based algorithm for single image generation that performs as well as a neural network without requiring a costly training phase. We ensure visual fidelity and diversity of the results by carefully choosing the initialization of the algorithm.
In the second part, we show that patch-based algorithms can benefit to modern techniques such as attention mechanisms. The use of attention has helped deep learning introduce long range dependencies but computing the full attention matrix is an expensive step with heavy memory and computational loads. We propose an efficient attention layer based on the stochastic algorithm PatchMatch, which is used for determining approximate nearest neighbors. Our layer has a greatly reduced memory complexity compared to other attention layers, scaling to high resolution images.

Venez nombreux!