提出跨分支注意力机制，提升点云自监督学习效果
A Cross Branch Fusion-Based Contrastive Learning Framework for Point Cloud Self-supervised Learning
- 引入子分支实现对比前的跨分支信息交互
- 无额外数据下下游任务性能达领先水平
- 适用于点云表征学习，尤其适合缺乏标注数据场景
对比学习是自监督学习中的核心方法，通常采用多分支策略，通过比较不同分支获取的隐含表示来训练编码器。对于多模态输入，同一物体的不同模态被送入不同分支；对于单模态数据，则对同一输入进行多种增强后送入不同分支。然而，现有对比学习框架均仅在最终损失阶段进行对比操作，各分支间在该阶段前无信息交换。本文针对无需额外训练数据的点云自监督学习，提出基于对比跨分支注意力的点云框架PoCCA，通过引入子分支，在损失前实现分支间的有效信息交互。实验表明，在不使用额外训练数据的情况下，所学表示在点云下游任务中达到当前最优性能。
原文摘要 · Abstract (English)
Contrastive learning is an essential method in self-supervised learning. It primarily employs a multi-branch strategy to compare latent representations obtained from different branches and train the encoder. In the case of multi-modal input, diverse modalities of the same object are fed into distinct branches. When using single-modal data, the same input undergoes various augmentations before being fed into different branches. However, all existing contrastive learning frameworks have so far only performed contrastive operations on the learned features at the final loss end, with no information exchange between different branches prior to this stage. In this paper, for point cloud unsupervised learning without the use of extra training data, we propose a Contrastive Cross-branch Attention-based framework for Point cloud data (termed PoCCA), to learn rich 3D point cloud representations. By introducing sub-branches, PoCCA allows information exchange between different branches before the loss end. Experimental results demonstrate that in the case of using no extra training data, the representations learned with our self-supervised model achieve state-of-the-art performances when used for downstream tasks on point clouds.
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。