SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization

TL;DR

This paper introduces SR-GNN, a relation-aware graph neural network that enhances fine-grained image categorization by capturing subtle structural details through context-aware features and attention mechanisms, outperforming existing methods.

Contribution

The paper proposes a novel relation-aware GNN model that leverages self-attention and context-aware features for improved fine-grained image classification without requiring bounding-box annotations.

Findings

Outperforms state-of-the-art methods on eight benchmark datasets.

Effectively captures subtle structural differences in images.

Improves recognition accuracy significantly.

Abstract

Over the past few years, a significant progress has been made in deep convolutional neural networks (CNNs)-based image recognition. This is mainly due to the strong ability of such networks in mining discriminative object pose and parts information from texture and shape. This is often inappropriate for fine-grained visual classification (FGVC) since it exhibits high intra-class and low inter-class variances due to occlusions, deformation, illuminations, etc. Thus, an expressive feature representation describing global structural information is a key to characterize an object/ scene. To this end, we propose a method that effectively captures subtle changes by aggregating context-aware features from most relevant image-regions and their importance in discriminating fine-grained categories avoiding the bounding-box and/or distinguishable part annotations. Our approach is inspired by the recent advancement in self-attention and graph neural networks (GNNs) approaches to include a simple yet effective relation-aware feature transformation and its refinement using a context-aware attention mechanism to boost the discriminability of the transformed feature in an end-to-end learning process. Our model is evaluated on eight benchmark datasets consisting of fine-grained objects and human-object interactions. It outperforms the state-of-the-art approaches by a significant margin in recognition accuracy.