Normalization Matters in Weakly Supervised Object Localization
This work addresses a key bottleneck in WSOL for computer vision researchers, though it is incremental as it focuses on improving existing methods rather than introducing a new paradigm.
The paper tackles the problem of inconsistent normalization in weakly supervised object localization (WSOL), showing that proper normalization of class activation maps (CAM) is crucial for performance. It proposes a new normalization method that achieves significant gains over conventional methods across three datasets and architectures.
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.