PT Unknown AU Pau Rodriguez Josep M. Gonfaus Guillem Cucurull Xavier Roca Jordi Gonzalez TI Attend and Rectify: A Gated Attention Mechanism for Fine-Grained Recovery BT 15th European Conference on Computer Vision PY 2018 BP 357 EP 372 VL 11212 DE Deep Learning; Convolutional Neural Networks; Attention AB 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. ER