Parsing Objects at a Finer Granularity: A Survey

TL;DR

This survey reviews fine-grained visual parsing, emphasizing the importance of understanding part relationships, consolidates recent research, and proposes new solutions based on part relationship learning to address key challenges.

Contribution

It introduces a new perspective focusing on learning part relationships, consolidates recent research with new taxonomies, and suggests future research directions.

Findings

Unified taxonomy for fine-grained parsing tasks.

Identification of key challenges in part segmentation and recognition.

Proposed solutions leveraging part relationship learning.

Abstract

Fine-grained visual parsing, including fine-grained part segmentation and fine-grained object recognition, has attracted considerable critical attention due to its importance in many real-world applications, e.g., agriculture, remote sensing, and space technologies. Predominant research efforts tackle these fine-grained sub-tasks following different paradigms, while the inherent relations between these tasks are neglected. Moreover, given most of the research remains fragmented, we conduct an in-depth study of the advanced work from a new perspective of learning the part relationship. In this perspective, we first consolidate recent research and benchmark syntheses with new taxonomies. Based on this consolidation, we revisit the universal challenges in fine-grained part segmentation and recognition tasks and propose new solutions by part relationship learning for these important challenges. Furthermore, we conclude several promising lines of research in fine-grained visual parsing for future research.