TY  - CONF
AU  - Pau Rodriguez
AU  - Josep M. Gonfaus
AU  - Guillem Cucurull
AU  - Xavier Roca
AU  - Jordi Gonzalez
A2  - ECCV
PY  - 2018//
TI  - Attend and Rectify: A Gated Attention Mechanism for Fine-Grained Recovery
T2  - LNCS
BT  - 15th European Conference on Computer Vision
SP  - 357
EP  - 372
VL  - 11212
KW  - Deep Learning
KW  - Convolutional Neural Networks
KW  - Attention
N2  - 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 other approaches, the proposed mechanism is modular, architecture-independent and efficient both in terms of parameters and computation required. Experiments show that networks augmented with our approach systematically improve their classification accuracy and become more robust to clutter. As a result, Wide Residual Networks augmented with our proposal surpasses the state of the art classification accuracies in CIFAR-10, the Adience gender recognition task, Stanford dogs, and UEC Food-100.
UR  - https://doi.org/10.1007/978-3-030-01237-3_22
L1  - http://refbase.cvc.uab.es/files/RGC2018.pdf
N1  - ISE; 600.098; 602.121; 600.119
ID  - Pau Rodriguez2018
ER  -