Attend and Rectify: a Gated Attention Mechanism for Fine-Grained Recovery
This addresses the problem of fine-grained visual recognition for computer vision applications, offering an incremental improvement through a modular and efficient attention method.
The paper tackles fine-grained recognition by introducing a novel attention mechanism that enhances Convolutional Neural Networks without part annotations, systematically improving classification accuracy and robustness to clutter, achieving state-of-the-art results on datasets like CIFAR-10 and Stanford dogs.
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.