Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange
This work addresses a specific challenge in point cloud scene understanding for indoor scenes, offering an incremental improvement in self-supervised learning by mitigating object dependencies.
The paper tackles the problem of neural networks exploiting strong inter-object dependencies in point cloud scene understanding, which can bypass individual object patterns, by introducing a self-supervised learning strategy that uses object exchange and context-aware feature learning to disentangle these dependencies. The method demonstrates superiority over existing SSL techniques, showing better robustness to environmental changes and applicability across diverse datasets.
In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object correlations. This can create a tendency for neural networks to exploit these strong dependencies, bypassing the individual object patterns. To address this challenge, we introduce a novel self-supervised learning (SSL) strategy. Our approach leverages both object patterns and contextual cues to produce robust features. It begins with the formulation of an object-exchanging strategy, where pairs of objects with comparable sizes are exchanged across different scenes, effectively disentangling the strong contextual dependencies. Subsequently, we introduce a context-aware feature learning strategy, which encodes object patterns without relying on their specific context by aggregating object features across various scenes. Our extensive experiments demonstrate the superiority of our method over existing SSL techniques, further showing its better robustness to environmental changes. Moreover, we showcase the applicability of our approach by transferring pre-trained models to diverse point cloud datasets.