ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization
This work addresses the problem of precise object localization for computer vision researchers, offering an incremental improvement over existing weakly supervised methods.
The paper tackles the problem of localizing objects in images using only image-level supervision, addressing the failure of previous methods to locate precise object boundaries by introducing context-aware guidance models. The result is a significant improvement in weakly supervised localization and detection on PASCAL VOC benchmarks.
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.