Normalization Matters in Weakly Supervised Object Localization

TL;DR

This paper highlights the importance of normalization in weakly supervised object localization, reviews existing methods, and proposes a new normalization technique that significantly improves localization accuracy across multiple datasets and architectures.

Contribution

The paper reviews normalization strategies in WSOL and introduces a novel normalization method that enhances CAM-based localization performance.

Findings

Significant performance gains with the proposed normalization across datasets.

Normalization choice depends on dataset properties.

The new method outperforms conventional min-max normalization.

Abstract

Weakly-supervised object localization (WSOL) enables finding an object using a dataset without any localization information. By simply training a classification model using only image-level annotations, the feature map of the model can be utilized as a score map for localization. In spite of many WSOL methods proposing novel strategies, there has not been any de facto standard about how to normalize the class activation map (CAM). Consequently, many WSOL methods have failed to fully exploit their own capacity because of the misuse of a normalization method. In this paper, we review many existing normalization methods and point out that they should be used according to the property of the given dataset. Additionally, we propose a new normalization method which substantially enhances the performance of any CAM-based WSOL methods. Using the proposed normalization method, we provide a comprehensive evaluation over three datasets (CUB, ImageNet and OpenImages) on three different architectures and observe significant performance gains over the conventional min-max normalization method in all the evaluated cases.