ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization

TL;DR

This paper introduces context-aware guidance models that leverage surrounding image regions to improve weakly supervised object localization, significantly enhancing accuracy on standard benchmarks.

Contribution

It proposes additive and contrastive context-aware models that extend Fast R-CNN for weakly supervised localization, addressing boundary precision issues.

Findings

Significant improvement in localization accuracy on PASCAL VOC datasets.

Effective use of surrounding context regions enhances weakly supervised detection.

Models outperform previous methods in benchmark evaluations.

Abstract

We aim to localize objects in images using image-level supervision only. Previous approaches to this problem mainly focus on discriminative object regions and often fail to locate precise object boundaries. We address this problem by introducing two types of context-aware guidance models, additive and contrastive models, that leverage their surrounding context regions to improve localization. The additive model encourages the predicted object region to be supported by its surrounding context region. The contrastive model encourages the predicted object region to be outstanding from its surrounding context region. Our approach benefits from the recent success of convolutional neural networks for object recognition and extends Fast R-CNN to weakly supervised object localization. Extensive experimental evaluation on the PASCAL VOC 2007 and 2012 benchmarks shows hat our context-aware approach significantly improves weakly supervised localization and detection.