← Search

Josep M. Gonfaus

2 accepted papers

2018

Attend and Rectify: a gated attention mechanism for fine-grained recovery

ECCV 2018poster

We propose a novel attention mechanism to enhance Convolutional Neural Networks for fine-grained recognition. It learns to attend to lower-level feature activations without requiring part annotations and uses these activations to update and rectify the output likelihood distribution. In contrast to…

2017

Regularizing CNNs with Locally Constrained Decorrelations

ICLR 2017poster

Regularization is key for deep learning since it allows training more complex models while keeping lower levels of overfitting. However, the most prevalent regularizations do not leverage all the capacity of the models since they rely on reducing the effective number of parameters. Feature decorrela…

Cited by 163SourceScholar