Boundary Knowledge Translation based Reference Semantic Segmentation

TL;DR

This paper introduces Ref-Net, a novel segmentation network that translates boundary knowledge from reference objects to segment similar objects in images, reducing reliance on large labeled datasets.

Contribution

Ref-Net combines boundary knowledge translation and reference-based segmentation, inspired by human visual cognition, to improve segmentation with fewer labeled samples.

Findings

Achieves comparable results to fully supervised methods with limited annotated data

Uses boundary discriminator branches for inner and outer boundary segmentation

Demonstrates effectiveness across six datasets

Abstract

Given a reference object of an unknown type in an image, human observers can effortlessly find the objects of the same category in another image and precisely tell their visual boundaries. Such visual cognition capability of humans seems absent from the current research spectrum of computer vision. Existing segmentation networks, for example, rely on a humongous amount of labeled data, which is laborious and costly to collect and annotate; besides, the performance of segmentation networks tend to downgrade as the number of the category increases. In this paper, we introduce a novel Reference semantic segmentation Network (Ref-Net) to conduct visual boundary knowledge translation. Ref-Net contains a Reference Segmentation Module (RSM) and a Boundary Knowledge Translation Module (BKTM). Inspired by the human recognition mechanism, RSM is devised only to segment the same category objects based on the features of the reference objects. BKTM, on the other hand, introduces two boundary discriminator branches to conduct inner and outer boundary segmentation of the target objectin an adversarial manner, and translate the annotated boundary knowledge of open-source datasets into the segmentation network. Exhaustive experiments demonstrate that, with tens of finely-grained annotated samples as guidance, Ref-Net achieves results on par with fully supervised methods on six datasets.