arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.13752cs.CV
收藏

定位与扩展:一种用于点云少样本语义分割的解耦框架

Localization and Expansion: A Decoupled Framework for Point Cloud Few-shot Semantic Segmentation

University of Science and Technology of China(中国科学技术大学);Deep Space Exploration Laboratory(深空探测实验室)

Zhaoyang Li, Yuan Wang, Wangkai Li, Rui Sun, Tianzhu Zhang

AI总结:

针对点云少样本语义分割中点级匹配脆弱和类内多样性导致的背景误激活与目标不完整问题,提出解耦定位与扩展框架DLE,通过结构定位模块和自扩展模块实现精确定位与完整目标分割,大幅超越现有方法。

摘要:

点云少样本语义分割(PC-FSS)旨在仅利用少量标注的支持样本,在给定的查询点云中分割新类别的目标。当前表现最优的原型学习方法采用源自支持样本的原型来指导查询点的分类。然而,点级匹配固有的脆弱性和普遍的类内多样性给这种跨实例匹配范式带来了巨大挑战,导致错误的背景激活或不完整的目标挖掘。在本工作中,我们提出了一种简单而有效的框架,其核心思想是解耦定位与扩展(DLE)。提出的DLE包含一个结构定位模块(SLM)和一个自扩展模块(SEM),具有多项优势。首先,通过SLM中的代理级相关性将结构信息注入匹配过程,从而能够精确定位可靠的目标区域。其次,在SEM中利用更可靠的物体内部相似性来推导完整目标,并引入保守的扩展策略以合理约束扩展过程。在两种具有挑战性的基准上的大量实验表明,在不同设置下,DLE大幅超越了以往的最先进方法。

英文摘要:

Point cloud few-shot semantic segmentation (PC-FSS) aims to segment targets of novel categories in a given query point cloud with only a few annotated support samples. The current top-performing prototypical learning methods employ prototypes originating from support samples to direct the classification of query points. However, the inherent fragility of point-level matching and the prevalent intra-class diversity pose great challenges to this cross-instance matching paradigm, leading to erroneous background activations or incomplete target excavation. In this work, we propose a simple yet effective framework in the spirit of Decoupled Localization and Expansion (DLE). The proposed DLE, including a structural localization module (SLM) and a self-expansion module (SEM), enjoys several merits. First, structural information is injected into the matching process through the agent-level correlation in SLM, and the confident target region can thus be precisely located. Second, more reliable intra-object similarity is harnessed in SEM to derive the complete target, and the conservative expansion strategy is introduced to reasonably constrain the expansion. Extensive experiments on two challenging benchmarks under different settings demonstrate that DLE outperforms previous state-of-the-art approaches by large margins.

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。

↑