2022/04/21 by Lu Zhang, Zhang, Lu, Siqi Zhang +5 · 1 citation
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Robotics (cs.RO)
paper · pdf · doi:10.48550/arxiv.2204.09847
openalex publication_date 2022/04/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Segmenting unseen objects is a crucial ability for the robot since it may encounter new environments during the operation. Recently, a popular solution is leveraging RGB-D features of large-scale synthetic data and directly applying the model to unseen real-world scenarios. However, the domain shift caused by the sim2real gap is inevitable, posing a crucial challenge to the segmentation model. In this paper, we emphasize the adaptation process across sim2real domains and model it as a learning problem on the BatchNorm parameters of a simulation-trained model. Specifically, we propose a novel non-parametric entropy objective, which formulates the learning objective for the test-time adaptation in an open-world manner. Then, a cross-modality knowledge distillation objective is further designed to encourage the test-time knowledge transfer for feature enhancement. Our approach can be efficiently implemented with only test images, without requiring annotations or revisiting the large-scale synthetic training data. Besides significant time savings, the proposed method consistently improves segmentation results on the overlap and boundary metrics, achieving state-of-the-art performance on unseen object instance segmentation.