Statistical Attention Localization (SAL): Methodology and Application to Object Classification

TL;DR

This paper introduces SAL, a three-step statistical attention localization method that improves object classification accuracy by focusing on salient regions, demonstrated on CIFAR-10 with an ensemble approach.

Contribution

The paper presents a novel SAL methodology that refines attention maps for better object localization and classification, integrated with SSL-based E-PixelHop for improved accuracy.

Findings

SAL improves classification accuracy on CIFAR-10

Ensembling attention region and whole image enhances results

SAL effectively localizes objects of various sizes and shapes

Abstract

A statistical attention localization (SAL) method is proposed to facilitate the object classification task in this work. SAL consists of three steps: 1) preliminary attention window selection via decision statistics, 2) attention map refinement, and 3) rectangular attention region finalization. SAL computes soft-decision scores of local squared windows and uses them to identify salient regions in Step 1. To accommodate object of various sizes and shapes, SAL refines the preliminary result and obtain an attention map of more flexible shape in Step 2. Finally, SAL yields a rectangular attention region using the refined attention map and bounding box regularization in Step 3. As an application, we adopt E-PixelHop, which is an object classification solution based on successive subspace learning (SSL), as the baseline. We apply SAL so as to obtain a cropped-out and resized attention region as an alternative input. Classification results of the whole image as well as the attention region are ensembled to achieve the highest classification accuracy. Experiments on the CIFAR-10 dataset are given to demonstrate the advantage of the SAL-assisted object classification method.