STDG: Semi-Teacher-Student Training Paradigram for Depth-guided One-stage Scene Graph Generation

TL;DR

STDG introduces a depth-guided, semi-teacher-student training approach for one-stage scene graph generation, effectively utilizing depth cues to improve environmental understanding without extra inference costs.

Contribution

The paper proposes a novel depth-guided architecture with semi-teacher-student training for scene graph generation, leveraging depth information more effectively than prior methods.

Findings

Significant performance improvements over baseline methods.

Effective utilization of depth cues enhances scene understanding.

No additional inference computational cost.

Abstract

Scene Graph Generation is a critical enabler of environmental comprehension for autonomous robotic systems. Most of existing methods, however, are often thwarted by the intricate dynamics of background complexity, which limits their ability to fully decode the inherent topological information of the environment. Additionally, the wealth of contextual information encapsulated within depth cues is often left untapped, rendering existing approaches less effective. To address these shortcomings, we present STDG, an avant-garde Depth-Guided One-Stage Scene Graph Generation methodology. The innovative architecture of STDG is a triad of custom-built modules: The Depth Guided HHA Representation Generation Module, the Depth Guided Semi-Teaching Network Learning Module, and the Depth Guided Scene Graph Generation Module. This trifecta of modules synergistically harnesses depth information, covering all aspects from depth signal generation and depth feature utilization, to the final scene graph prediction. Importantly, this is achieved without imposing additional computational burden during the inference phase. Experimental results confirm that our method significantly enhances the performance of one-stage scene graph generation baselines.