面向3D视觉定位的多分支协作学习网络
Multi-branch Collaborative Learning Network for 3D Visual Grounding
AI总结：
针对现有3D指称表达理解与分割协作方法协作效率受限的问题，提出含独立任务分支及RSA、ASA模块的MCLN框架，实现两任务精准对齐协作，在两项任务上均达SOTA性能。
摘要：
3D指称表达理解（3D referring expression comprehension, 3DREC）与3D指称表达分割（3D referring expression segmentation, 3DRES）目标存在重叠，具备协作潜力。但现有协作方法大多依赖一个任务的结果为另一任务做预测，限制了有效协作。我们认为为3DREC和3DRES任务采用独立分支可增强模型学习各任务特定信息的能力，使其习得互补知识。据此我们提出MCLN（多分支协作学习网络）框架，为两个任务分设独立分支，既能对各任务进行针对性探索，又能实现分支间有效协同。此外，为促进分支间相互强化，我们引入相对超点聚合（Relative Superpoint Aggregation, RSA）模块与自适应软对齐（Adaptive Soft Alignment, ASA）模块，可显著助力两个分支预测结果的精准对齐，引导模块将更多注意力分配到关键位置。综合实验评估表明，所提方法在3DREC和3DRES任务上均达到SOTA性能，其中3DREC的Acc@0.5提升2.05%，3DRES的mIoU提升3.96%。
英文摘要：
3D referring expression comprehension (3DREC) and segmentation (3DRES) have overlapping objectives, indicating their potential for collaboration. However, existing collaborative approaches predominantly depend on the results of one task to make predictions for the other, limiting effective collaboration. We argue that employing separate branches for 3DREC and 3DRES tasks enhances the model's capacity to learn specific information for each task, enabling them to acquire complementary knowledge. Thus, we propose the MCLN framework, which includes independent branches for 3DREC and 3DRES tasks. This enables dedicated exploration of each task and effective coordination between the branches. Furthermore, to facilitate mutual reinforcement between these branches, we introduce a Relative Superpoint Aggregation (RSA) module and an Adaptive Soft Alignment (ASA) module. These modules significantly contribute to the precise alignment of prediction results from the two branches, directing the module to allocate increased attention to key positions. Comprehensive experimental evaluation demonstrates that our proposed method achieves state-of-the-art performance on both the 3DREC and 3DRES tasks, with an increase of 2.05% in Acc@0.5 for 3DREC and 3.96% in mIoU for 3DRES.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
