# Attend and Rectify: a Gated Attention Mechanism for Fine-Grained Recovery

arXiv: https://arxiv.org/abs/1807.07320 · HTML: https://mlsanity.com/paper/1807.07320/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2018.

## Built on by (most cited first, 2 of 2)

- [Parsing Objects at a Finer Granularity: A Survey](https://mlsanity.com/paper/2212.13693/) (2022)
- [Interpretable Attention Guided Network for Fine-grained Visual Classification](https://mlsanity.com/paper/2103.04701/) (2021)

## Abstract (arXiv)

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.