All the attention you need: Global-local, spatial-channel attention for image retrieval

We address representation learning for large-scale instance-level image retrieval. Apart from backbone, training pipelines and loss functions, popular approaches have focused on different spatial pooling and attention mechanisms, which are at the core of learning a powerful global image representation. There are different forms of attention according to the interaction of elements of the feature tensor (local and global) and the dimensions where it is applied (spatial and channel). Unfortunately, each study addresses only one or two forms of attention and applies it to different problems like classification, detection or retrieval. We present global-local attention module (GLAM), which is attached at the end of a backbone network and incorporates all four forms of attention: local and global, spatial and channel. We obtain a new feature tensor and, by spatial pooling, we learn a powerful embedding for image retrieval. Focusing on global descriptors, we provide empirical evidence of the interaction of all forms of attention and improve the state of the art on standard benchmarks.

Automated summary

We focus on representation learning for large-scale instance-level image retrieval. We propose a global-local attention module (GLAM) that incorporates all forms of attention, including local and global, spatial and channel. By applying these attention mechanisms, we obtain a powerful image representation and achieve state-of-the-art performance on standard benchmarks.