Embodied Domain Adaptation for Object Detection
This addresses the challenge of adapting object detectors to diverse and changing indoor settings for mobile robots, representing an incremental improvement over existing open-vocabulary methods.
The paper tackles the problem of domain shift in object detection for mobile robots in indoor environments by introducing a source-free domain adaptation approach, achieving significant gains in zero-shot detection performance and flexible adaptation to dynamic conditions.
Mobile robots rely on object detectors for perception and object localization in indoor environments. However, standard closed-set methods struggle to handle the diverse objects and dynamic conditions encountered in real homes and labs. Open-vocabulary object detection (OVOD), driven by Vision Language Models (VLMs), extends beyond fixed labels but still struggles with domain shifts in indoor environments. We introduce a Source-Free Domain Adaptation (SFDA) approach that adapts a pre-trained model without accessing source data. We refine pseudo labels via temporal clustering, employ multi-scale threshold fusion, and apply a Mean Teacher framework with contrastive learning. Our Embodied Domain Adaptation for Object Detection (EDAOD) benchmark evaluates adaptation under sequential changes in lighting, layout, and object diversity. Our experiments show significant gains in zero-shot detection performance and flexible adaptation to dynamic indoor conditions.