Attend, Infer, Repeat: Fast Scene Understanding with Generative Models

23 Mar 2016

The Attend-Infer-Repeat Architecture

We present a framework for efficient inference in structured image models that explicitly reason about objects. We achieve this by performing probabilistic inference using a recurrent neural network that attends to scene elements and processes them one at a time. Crucially, the model itself learns to choose the appropriate number of inference steps. We use this scheme to learn to perform inference in partially specified 2D models (variable-sized variational auto-encoders) and fully specified 3D models (probabilistic renderers).

We show that such models learn to identify multiple objects – counting, locating and classifying the elements of a scene – without any supervision, e.g., decomposing 3D images with various numbers of objects in a single forward pass of a neural network. We further show that the networks produce accurate inferences when compared to supervised counterparts, and that their structure leads to improved generalization.

Downloads

Paper, Video Stream, Video MP4

Video

Stream, MP4

BibTex

@inproceedings{Eslami2016, 
    author = {S. M. Ali Eslami and Nicolas Heess and Theophane Weber and 
              Yuval Tassa and Koray Kavukcuoglu and Geoffrey E. Hinton}, 
    title = {Attend, Infer, Repeat: Fast Scene Understanding with Generative Models},
    year = {2016}
}