$A^2$-Nets: Double Attention Networks

Understand

Learning to capture long-range relations is fundamental to image/video recognition.

• Existing CNN models generally rely on increasing depth to model such relations which is highly inefficient.
• In this work, we propose the "double attention block", a novel component that aggregates and propagates informative global features from the entire spatio-temporal space of input images/videos, enabling subsequent convolution layers to access features from the entire space efficiently.
• The component is designed with a double attention mechanism in two steps, where the first step gathers features from the entire space into a compact set through second-order attention pooling and the second step adaptively selects and distributes features to each location via another attention.