40 citations · 131 across the 18 of their papers we have counts for
3 papers · 1 filter
Feature discriminativity estimation in CNNs for transfer learning
Victor Gimenez-Abalos, Armand Vilalta, Dario Garcia-Gasulla +2
The purpose of feature extraction on convolutional neural networks is to reuse deep representations learnt for a pre-trained model to solve a new, potentially unrelated problem. Ho…
Building Graph Representations of Deep Vector Embeddings
Dario Garcia-Gasulla, Armand Vilalta, Ferran Parés +5
Patterns stored within pre-trained deep neural networks compose large and powerful descriptive languages that can be used for many different purposes. Typically, deep network repre…
On the Behavior of Convolutional Nets for Feature Extraction
Dario Garcia-Gasulla, Ferran Parés, Armand Vilalta +5
Deep neural networks are representation learning techniques. During training, a deep net is capable of generating a descriptive language of unprecedented size and detail in machine…