Xiaolin Zhang

TL;DR: This article proposes a simple yet effective similarity guidance network to tackle the one-shot (SG-One) segmentation problem, aiming at predicting the segmentation mask of a query image with the reference to one densely labeled support image of the same category.

TL;DR: Adversarial complementary learning (ACoL) as discussed by the authors leverages one classification branch to dynamically localize some discriminative object regions during the forward pass, which enables the counterpart classifier to discover new and complementary object regions by erasing its discovered regions from the feature maps.

TL;DR: Li et al. as mentioned in this paper proposed to generate self-produced guidance (SPG) masks which separate the foreground object from the background to provide the classification networks with spatial correlation information of pixels.

TL;DR: This paper proposes to leverage pixel-level similarities across different objects for learning more accurate object locations in a complementary way, and proposes two kinds of constraints that can benefit each other to learn consistent pixel- level features within the same categories, and improve the quality of localization maps.