斑块的崩塌

摘要

观察图像中的某些区块会降低其他区块的不确定性。这些区块的具现化会缩减其余每个区块特征的分布熵，类似于量子力学中粒子波函数的坍缩。这种现象可直观地称为区块坍缩。为识别目标区域坍缩过程中最依赖的区块，我们训练了一种自动编码器，通过软选择区块子集来重建每个目标区块。根据各区块的PageRank分值绘制这些学习到的依赖关系图，可揭示实现图像重构的最优区块顺序。实验表明遵循该顺序能提升多种掩码图像建模方法的性能：首先通过重新训练最先进的自回归模型MAR可提升图像生成效果；继而提出视觉Transformer仅接触坍缩顺序中高权重区块的图像分类新范式，仅需观察22%的高权重区块即可实现高精度分类。通过这些实验，我们提出以区块坍缩作为新型图像建模视角来提升视觉效率。项目代码已开源于https://github.com/wguo-ai/CoP。

English

Observing certain patches in an image reduces the uncertainty of others. Their realization lowers the distribution entropy of each remaining patch feature, analogous to collapsing a particle's wave function in quantum mechanics. This phenomenon can intuitively be called patch collapse. To identify which patches are most relied on during a target region's collapse, we learn an autoencoder that softly selects a subset of patches to reconstruct each target patch. Graphing these learned dependencies for each patch's PageRank score reveals the optimal patch order to realize an image. We show that respecting this order benefits various masked image modeling methods. First, autoregressive image generation can be boosted by retraining the state-of-the-art model MAR. Next, we introduce a new setup for image classification by exposing Vision Transformers only to high-rank patches in the collapse order. Seeing 22\% of such patches is sufficient to achieve high accuracy. With these experiments, we propose patch collapse as a novel image modeling perspective that promotes vision efficiency. Our project is available at https://github.com/wguo-ai/CoP .

斑块的崩塌

The Collapse of Patches

摘要

Support