GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild

TL;DR

This paper introduces GMNet, a graph matching network that improves large-scale part semantic segmentation by leveraging object-level context and part spatial relationships, achieving state-of-the-art results.

Contribution

The work presents a novel framework combining class-conditioning and adjacency graph modules for enhanced part segmentation in complex scenes.

Findings

Achieves state-of-the-art performance on Pascal-Part dataset.

Effectively models spatial relationships between parts.

Improves segmentation accuracy in cluttered scenes.

Abstract

The semantic segmentation of parts of objects in the wild is a challenging task in which multiple instances of objects and multiple parts within those objects must be detected in the scene. This problem remains nowadays very marginally explored, despite its fundamental importance towards detailed object understanding. In this work, we propose a novel framework combining higher object-level context conditioning and part-level spatial relationships to address the task. To tackle object-level ambiguity, a class-conditioning module is introduced to retain class-level semantics when learning parts-level semantics. In this way, mid-level features carry also this information prior to the decoding stage. To tackle part-level ambiguity and localization we propose a novel adjacency graph-based module that aims at matching the relative spatial relationships between ground truth and predicted parts. The experimental evaluation on the Pascal-Part dataset shows that we achieve state-of-the-art results on this task.