Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition

Understand

The visual system processes a scene using a sequence of selective glimpses, each driven by spatial and object-based attention.

• These glimpses reflect what is relevant to the ongoing task and are selected through recurrent processing and recognition of the objects in the scene.
• In contrast, most models treat attention selection and recognition as separate stages in a feedforward process.
• Here we show that using capsule networks to create an object-centric hidden representation in an encoder-decoder model with iterative glimpse attention yields effective integration of attention and recognition.