Closed-Loop Transfer for Weakly-supervised Affordance Grounding

TL;DR

This paper presents LoopTrans, a closed-loop framework for weakly-supervised affordance grounding that improves knowledge transfer between exocentric and egocentric images, enabling better localization of interaction regions even in occluded scenarios.

Contribution

Introduction of LoopTrans, a novel closed-loop transfer framework with cross-modal localization and denoising distillation for enhanced affordance grounding.

Findings

Achieves consistent improvements across all metrics on benchmarks.

Effectively handles occluded interaction regions.

Enhances knowledge extraction through bidirectional transfer.

Abstract

Humans can perform previously unexperienced interactions with novel objects simply by observing others engage with them. Weakly-supervised affordance grounding mimics this process by learning to locate object regions that enable actions on egocentric images, using exocentric interaction images with image-level annotations. However, extracting affordance knowledge solely from exocentric images and transferring it one-way to egocentric images limits the applicability of previous works in complex interaction scenarios. Instead, this study introduces LoopTrans, a novel closed-loop framework that not only transfers knowledge from exocentric to egocentric but also transfers back to enhance exocentric knowledge extraction. Within LoopTrans, several innovative mechanisms are introduced, including unified cross-modal localization and denoising knowledge distillation, to bridge domain gaps between object-centered egocentric and interaction-centered exocentric images while enhancing knowledge transfer. Experiments show that LoopTrans achieves consistent improvements across all metrics on image and video benchmarks, even handling challenging scenarios where object interaction regions are fully occluded by the human body.