改进对象中心学习的离散表示，提升物体特征提取精度。
Organized Grouped Discrete Representation for Object-Centric Learning
- 按属性组织通道，避免错误分组导致的信息损失
- 在无监督分割中优于现有方法，提升主流模型性能
- 适合做物体识别与图像生成相关研究的开发者参考
对象中心学习（OCL）将密集的图像或视频像素表示为稀疏的对象特征。现有方法使用变分自编码器（VAE）模板特征构成离散表示，以减少像素级冗余并引导对象级特征聚合。最新进展组离散表示（GDR）进一步将模板特征分解为属性，但其朴素的通道分组可能错误地将不同属性的通道合并，导致次优的模板属性离散化，造成信息丢失并降低表达能力。本文提出有组织的组离散表示（OGDR），通过将属于同一属性的通道正确聚集，实现更准确的特征到属性的分解。在无监督分割实验中，OGDR全面优于GDR，显著提升经典基于Transformer的OCL方法性能，甚至改善最先进的基于扩散模型的方法。代码本PCA与表示相似性分析表明，相比GDR，OGDR更好消除冗余、保留信息，从而更有效地指导对象表征学习。源代码见补充材料。
原文摘要 · Abstract (English)
Object-Centric Learning (OCL) represents dense image or video pixels as sparse object features. Representative methods utilize discrete representation composed of Variational Autoencoder (VAE) template features to suppress pixel-level information redundancy and guide object-level feature aggregation. The most recent advancement, Grouped Discrete Representation (GDR), further decomposes these template features into attributes. However, its naive channel grouping as decomposition may erroneously group channels belonging to different attributes together and discretize them as sub-optimal template attributes, which losses information and harms expressivity. We propose Organized GDR (OGDR) to organize channels belonging to the same attributes together for correct decomposition from features into attributes. In unsupervised segmentation experiments, OGDR is fully superior to GDR in augmentating classical transformer-based OCL methods; it even improves state-of-the-art diffusion-based ones. Codebook PCA and representation similarity analyses show that compared with GDR, our OGDR eliminates redundancy and preserves information better for guiding object representation learning. The source code is available in the supplementary material.
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。