提出竞争感知的Transformer架构，提升3D实例分割精度与收敛速度。
CompetitorFormer: Competitor Transformer for 3D Instance Segmentation
- 引入竞争感知设计，缓解查询间竞争问题
- 在ScanNet、S3DIS等数据集上显著提升分割性能
- 可无缝接入现有框架，适合3D视觉任务研究者
基于Transformer的方法已成为3D实例分割的主流。这些方法通过实例查询预测实例掩码，并根据分类置信度和IoU分数排序，选择最高分作为最终结果。然而，当前模型使用的查询数量通常高于场景中的实例数量，导致多个查询预测同一实例，但仅一个查询被优化。低层解码器中查询得分相近，使主导查询难以快速脱颖而出，影响模型准确率与收敛效率。该现象称为查询间竞争。为此，我们提出一系列即插即用的竞争导向设计，统称为CompetitorFormer，旨在减少竞争并促进主导查询生成。实验表明，将这些设计集成到最先进的框架中，在多个数据集上均实现了显著的性能提升。
原文摘要 · Abstract (English)
Transformer-based methods have become the dominant approach for 3D instance segmentation. These methods predict instance masks via instance queries, ranking them by classification confidence and IoU scores to select the top prediction as the final outcome. However, it has been observed that the current models employ a fixed and higher number of queries than the instances present within a scene. In such instances, multiple queries predict the same instance, yet only a single query is ultimately optimized. The close scores of queries in the lower-level decoders make it challenging for the dominant query to distinguish itself rapidly, which ultimately impairs the model's accuracy and convergence efficiency. This phenomenon is referred to as inter-query competition. To address this challenge, we put forth a series of plug-and-play competition-oriented designs, collectively designated as the CompetitorFormer, with the aim of reducing competition and facilitating a dominant query. Experiments showed that integrating our designs with state-of-the-art frameworks consistently resulted in significant performance improvements in 3D instance segmentation across a range of datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。