Attend and Rectify: a Gated Attention Mechanism for Fine-Grained Recovery
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.
PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract
Datasets
CIFAR-10
CIFAR-100
MNIST
CUB-200-2011
Adience
Results from the Paper
Ranked #106 on
Image Classification
on CIFAR-100
(using extra training data)
