通过关注点云关键部位，提升未知类别识别能力。
SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds
- 分部件识别重要与不重要区域，针对性生成未知样本。
- 在多个数据集上准确率超越现有最佳方法。
- 适合需要区分已知与未知3D物体的场景使用。
深度学习虽显著提升了3D物体识别能力，但多数模型仅适用于闭集场景，难以处理现实应用中的未知样本。开放集识别（OSR）通过让模型既能分类已知类别，又能识别新类别来弥补这一缺陷。然而，现有方法依赖全局特征区分已知与未知类别，将整个物体视为统一整体，忽略了不同部分的语义重要性差异。为此，本文提出显著性感知结构分离（SASep），包含：(i) 可调语义分解（TSD）模块，用于将物体语义分解为重要与不重要部分；(ii) 几何合成策略（GSS），通过组合不重要部分生成伪未知样本；(iii) 合成辅助边界分离（SMS）模块，通过扩展类别间特征分布来增强特征级分离。三者协同提升几何与特征表示，显著增强模型对已知与未知类别的区分能力。实验表明，SASep在3D OSR任务中表现优异，超越现有最先进方法。
原文摘要 · Abstract (English)
Recent advancements in deep learning have greatly enhanced 3D object recognition, but most models are limited to closed-set scenarios, unable to handle unknown samples in real-world applications. Open-set recognition (OSR) addresses this limitation by enabling models to both classify known classes and identify novel classes. However, current OSR methods rely on global features to differentiate known and unknown classes, treating the entire object uniformly and overlooking the varying semantic importance of its different parts. To address this gap, we propose Salience-Aware Structured Separation (SASep), which includes (i) a tunable semantic decomposition (TSD) module to semantically decompose objects into important and unimportant parts, (ii) a geometric synthesis strategy (GSS) to generate pseudo-unknown objects by combining these unimportant parts, and (iii) a synth-aided margin separation (SMS) module to enhance feature-level separation by expanding the feature distributions between classes. Together, these components improve both geometric and feature representations, enhancing the model's ability to effectively distinguish known and unknown classes. Experimental results show that SASep achieves superior performance in 3D OSR, outperforming existing state-of-the-art methods.
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。