# Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization

## TL;DR

The paper introduces 'Hide-and-Seek', a novel weakly-supervised framework that enhances object and action localization by forcing networks to identify all relevant parts through random patch hiding during training.

## Contribution

It presents a simple yet effective method that improves localization accuracy by encouraging networks to consider all relevant object parts, applicable to both images and videos.

## Key findings

- Outperforms previous methods on ILSVRC dataset for object localization.
- Effectively extends to weakly-supervised action localization.
- Requires only minimal modifications to existing networks.

## Abstract

We propose `Hide-and-Seek', a weakly-supervised framework that aims to improve object localization in images and action localization in videos. Most existing weakly-supervised methods localize only the most discriminative parts of an object rather than all relevant parts, which leads to suboptimal performance. Our key idea is to hide patches in a training image randomly, forcing the network to seek other relevant parts when the most discriminative part is hidden. Our approach only needs to modify the input image and can work with any network designed for object localization. During testing, we do not need to hide any patches. Our Hide-and-Seek approach obtains superior performance compared to previous methods for weakly-supervised object localization on the ILSVRC dataset. We also demonstrate that our framework can be easily extended to weakly-supervised action localization.