Unseen Object Instance Segmentation with Fully Test-time RGB-D Embeddings Adaptation | |
Lu Zhang; Siqi Zhang; Xu Yang; Hong Qiao; Zhiyong Li | |
2023-05 | |
会议日期 | May 29 - June 2, 2023 |
会议地点 | London, UK |
英文摘要 | 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 em-phasize the adaptation process across sim2real domains and model it as a learning problem on the BatchNorm param-eters 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. |
会议录出版者 | IEEE |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/57277] |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Zhiyong Li |
作者单位 | State Key Laboratory of Multimodal Artifi cial In- telligence Systems, Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Lu Zhang,Siqi Zhang,Xu Yang,et al. Unseen Object Instance Segmentation with Fully Test-time RGB-D Embeddings Adaptation[C]. 见:. London, UK. May 29 - June 2, 2023. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论