arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.01726cs.CV
收藏

分组离散表示引导以对象为中心的学习

Grouped Discrete Representation Guides Object-Centric Learning

Rongzhen Zhao, Vivienne Wang, Juho Kannala, Joni Pajarinen

AI总结:

提出分组离散表示(GDR)方法,通过将特征分组为属性并用元组数索引,解决了基于Transformer的OCL中特征泛化和收敛启发不足的问题,显著提升了模型的收敛性与泛化能力。

摘要:

类似于人类将视觉场景感知为对象,Object-Centric Learning (OCL) 能将密集图像或视频抽象为稀疏的对象级特征。基于 Transformer 的 OCL 因离散表示的解码指导而能很好地处理复杂纹理,该离散表示是通过使用 codebook 的模板特征对图像或视频特征图中的噪声特征进行离散化而获得的。然而,将特征视为最小单元忽略了其组成属性,从而阻碍了模型泛化;用自然数对特征进行索引丢失了属性级的共性和特征,从而削弱了对模型收敛的启发。我们提出 Grouped Discrete Representation (GDR) 来解决这些问题,通过将特征分组为属性并用元组数进行索引。在不同查询初始化、数据集模态和模型架构的大量实验中,GDR 持续提升了收敛性和泛化能力。可视化表明我们的方法有效捕获了特征中的属性级信息。源代码将在被接受后提供。

英文摘要:

Similar to humans perceiving visual scenes as objects, Object-Centric Learning (OCL) can abstract dense images or videos into sparse object-level features. Transformer-based OCL handles complex textures well due to the decoding guidance of discrete representation, obtained by discretizing noisy features in image or video feature maps using template features from a codebook. However, treating features as minimal units overlooks their composing attributes, thus impeding model generalization; indexing features with natural numbers loses attribute-level commonalities and characteristics, thus diminishing heuristics for model convergence. We propose \textit{Grouped Discrete Representation} (GDR) to address these issues by grouping features into attributes and indexing them with tuple numbers. In extensive experiments across different query initializations, dataset modalities, and model architectures, GDR consistently improves convergence and generalizability. Visualizations show that our method effectively captures attribute-level information in features. The source code will be available upon acceptance.

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。

↑