UniRef++：在空间与时间维度中分割所有参考对象

UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces

December 25, 2023

作者: Jiannan Wu, Yi Jiang, Bin Yan, Huchuan Lu, Zehuan Yuan, Ping Luo

cs.AI

摘要

基于参考的物体分割任务，包括指代图像分割（RIS）、小样本图像分割（FSS）、指代视频对象分割（RVOS）和视频对象分割（VOS），旨在通过语言或标注掩码作为参考来分割特定对象。尽管各个领域已取得显著进展，但现有方法均针对特定任务设计且发展方向各异，这阻碍了这些任务多任务能力的激活。本研究旨在打破当前碎片化局面，提出UniRef++框架，通过单一架构统一上述四种基于参考的物体分割任务。该方案的核心是提出的UniFusion模块，该模块通过多模态融合机制处理不同任务对应的参考信息，并采用统一的Transformer架构实现实例级分割。通过这种一体化设计，UniRef++能够在广泛基准数据集上进行联合训练，并在运行时通过指定相应参考灵活完成多任务。我们在多个基准测试上评估了统一模型，大量实验结果表明：UniRef++在RIS和RVOS任务上达到最先进性能，在FSS和VOS任务上使用参数共享网络也能保持竞争力。此外，我们证明所提出的UniFusion模块可轻松集成到当前先进的基础模型SAM中，通过参数高效微调即可获得理想效果。代码和模型已开源：https://github.com/FoundationVision/UniRef。

English

The reference-based object segmentation tasks, namely referring image segmentation (RIS), few-shot image segmentation (FSS), referring video object segmentation (RVOS), and video object segmentation (VOS), aim to segment a specific object by utilizing either language or annotated masks as references. Despite significant progress in each respective field, current methods are task-specifically designed and developed in different directions, which hinders the activation of multi-task capabilities for these tasks. In this work, we end the current fragmented situation and propose UniRef++ to unify the four reference-based object segmentation tasks with a single architecture. At the heart of our approach is the proposed UniFusion module which performs multiway-fusion for handling different tasks with respect to their specified references. And a unified Transformer architecture is then adopted for achieving instance-level segmentation. With the unified designs, UniRef++ can be jointly trained on a broad range of benchmarks and can flexibly complete multiple tasks at run-time by specifying the corresponding references. We evaluate our unified models on various benchmarks. Extensive experimental results indicate that our proposed UniRef++ achieves state-of-the-art performance on RIS and RVOS, and performs competitively on FSS and VOS with a parameter-shared network. Moreover, we showcase that the proposed UniFusion module could be easily incorporated into the current advanced foundation model SAM and obtain satisfactory results with parameter-efficient finetuning. Codes and models are available at https://github.com/FoundationVision/UniRef.