Addressing a fundamental limitation in deep vision models: lack of spatial attention

TL;DR

This paper highlights a key limitation in deep vision models' lack of spatial attention, proposing two methods to enable selective processing of image regions for improved efficiency.

Contribution

It introduces two novel approaches for incorporating spatial attention into deep vision models, mimicking human visual selectivity to enhance efficiency.

Findings

Proposed selective convolution and pooling based on change maps.

Implemented segmentation-based region processing.

Code available at GitHub.

Abstract

The primary aim of this manuscript is to underscore a significant limitation in current deep learning models, particularly vision models. Unlike human vision, which efficiently selects only the essential visual areas for further processing, leading to high speed and low energy consumption, deep vision models process the entire image. In this work, we examine this issue from a broader perspective and propose two solutions that could pave the way for the next generation of more efficient vision models. In the first solution, convolution and pooling operations are selectively applied to altered regions, with a change map sent to subsequent layers. This map indicates which computations need to be repeated. In the second solution, only the modified regions are processed by a semantic segmentation model, and the resulting segments are inserted into the corresponding areas of the previous output map. The code is available at https://github.com/aliborji/spatial_attention.