研究排列不变的离散表示学习以空间对齐图像
Investigating Permutation-Invariant Discrete Representation Learning for Spatially Aligned Images
AI总结：
本文探讨了空间对齐数据的离散表示是否需要位置信息，提出PI-VQ模型，通过约束潜在代码无位置信息，实现全局语义特征捕捉和直接图像插值，同时引入匹配量化提升信息容量。
摘要：
向量量化方法（VQ-VAE, VQ-GAN）学习图像的离散神经表示，但这些表示本质上是位置依赖的：代码在空间上排列且上下文纠缠，需要自回归或扩散先验来建模依赖关系。本文探讨是否需要位置信息来表示空间对齐数据。我们提出排列不变的向量量化自编码器（PI-VQ），其中潜在代码被约束不携带位置信息。我们发现这种约束促使代码捕捉全局语义特征，并允许在不使用学习先验的情况下直接插值图像。为解决排列不变表示的信息容量减少问题，我们引入匹配量化，一种基于最优二部匹配的向量量化算法，相对于朴素最近邻量化，有效瓶颈容量增加3.5倍。学习代码的组成结构进一步使插值采样成为可能，允许在单次前向传递中合成新图像。我们在CelebA、CelebA-HQ和FFHQ上评估PI-VQ，获得与我们方法生成图像的精度、密度和覆盖率指标具有竞争力的结果。我们讨论了无位置表示的固有权衡，包括潜在代码的分离性和可解释性，指出了未来研究的多个方向。
英文摘要：
Vector quantization approaches (VQ-VAE, VQ-GAN) learn discrete neural representations of images, but these representations are inherently position-dependent: codes are spatially arranged and contextually entangled, requiring autoregressive or diffusion-based priors to model their dependencies at sample time. In this work, we ask whether positional information is necessary for discrete representations of spatially aligned data. We propose the permutation-invariant vector-quantized autoencoder (PI-VQ), in which latent codes are constrained to carry no positional information. We find that this constraint encourages codes to capture global, semantic features, and enables direct interpolation between images without a learned prior. To address the reduced information capacity of permutation-invariant representations, we introduce matching quantization, a vector quantization algorithm based on optimal bipartite matching that increases effective bottleneck capacity by $3.5\times$ relative to naive nearest-neighbour quantization. The compositional structure of the learned codes further enables interpolation-based sampling, allowing synthesis of novel images in a single forward pass. We evaluate PI-VQ on CelebA, CelebA-HQ and FFHQ, obtaining competitive precision, density and coverage metrics for images synthesised with our approach. We discuss the trade-offs inherent to position-free representations, including separability and interpretability of the latent codes, pointing to numerous directions for future work.
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。
