Where to Focus: Deep Attention-based Spatially Recurrent Bilinear Networks for Fine-Grained Visual Recognition

TL;DR

This paper introduces a novel attention-based deep neural network that combines two CNNs, bilinear pooling, and spatial recurrent attention to improve fine-grained visual recognition by focusing on critical object regions despite appearance variations.

Contribution

It proposes an end-to-end trainable model integrating two-stream CNNs, bilinear pooling, and spatially recurrent attention for more accurate part detection and feature extraction in fine-grained recognition.

Findings

Outperforms existing methods in fine-grained image classification.

Effective in person re-identification tasks.

Shows robustness to occlusions and viewpoint changes.

Abstract

Fine-grained visual recognition typically depends on modeling subtle difference from object parts. However, these parts often exhibit dramatic visual variations such as occlusions, viewpoints, and spatial transformations, making it hard to detect. In this paper, we present a novel attention-based model to automatically, selectively and accurately focus on critical object regions with higher importance against appearance variations. Given an image, two different Convolutional Neural Networks (CNNs) are constructed, where the outputs of two CNNs are correlated through bilinear pooling to simultaneously focus on discriminative regions and extract relevant features. To capture spatial distributions among the local regions with visual attention, soft attention based spatial Long-Short Term Memory units (LSTMs) are incorporated to realize spatially recurrent yet visually selective over local input patterns. All the above intuitions equip our network with the following novel model: two-stream CNN layers, bilinear pooling layer, spatial recurrent layer with location attention are jointly trained via an end-to-end fashion to serve as the part detector and feature extractor, whereby relevant features are localized and extracted attentively. We show the significance of our network against two well-known visual recognition tasks: fine-grained image classification and person re-identification.