MacTok：面向图像生成的鲁棒连续分词器
MacTok: Robust Continuous Tokenization for Image Generation
MacTok 通过随机掩码和 DINO 引导的语义掩码来正则化潜变量学习，结合全局与局部表征对齐，防止少词元下的后验坍塌，为视觉生成提供了一种高效的一维连续分词方案，可直接用于扩散模型的前端压缩。
原文依据 MacTok applies both random masking to regularize latent learning and DINO-guided semantic masking to emphasize informative regions in images
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论连续图像分词器能够实现高效的视觉生成，而基于变分框架的分词器可以通过 KL 正则化学习平滑、结构化的潜变量表示。然而，当使用较少词元时，这往往会导致后验坍塌，即编码器无法将信息丰富的特征编码到压缩的潜变量空间中。为解决这一问题，我们提出了 MacTok，一种掩码增强的一维连续分词器，利用图像掩码和表征对齐来防止坍塌，同时学习紧凑且鲁棒的表示。MacTok 同时应用随机掩码来正则化潜变量学习，以及 DINO 引导的语义掩码来强调图像中的信息区域，迫使模型从不完整的视觉证据中编码鲁棒的语义。结合全局和局部表征对齐，MacTok 在高度压缩的一维潜变量空间中保留了丰富的判别信息，仅需 64 或 128 个词元。在 ImageNet 上，MacTok 与 SiT-XL 结合时，在 256x256 分辨率下取得了具有竞争力的 gFID 1.44，在 512x512 分辨率下取得了最优的 1.52，同时将词元使用量减少了高达 64 倍。这些结果证实，掩码和语义引导共同防止了后验坍塌，实现了高效、高保真的分词。
英文原文摘要 1275 字符
Continuous image tokenizers enable efficient visual generation, and those based on variational frameworks can learn smooth, structured latent representations through KL regularization. Yet this often leads to posterior collapse when using fewer tokens, where the encoder fails to encode informative features into the compressed latent space. To address this, we introduce **MacTok**, a **M**asked **A**ugmenting 1D **C**ontinuous **Tok**enizer that leverages image masking and representation alignment to prevent collapse while learning compact and robust representations. MacTok applies both random masking to regularize latent learning and DINO-guided semantic masking to emphasize informative regions in images, forcing the model to encode robust semantics from incomplete visual evidence. Combined with global and local representation alignment, MacTok preserves rich discriminative information in a highly compressed 1D latent space, requiring only 64 or 128 tokens. On ImageNet, MacTok achieves a competitive gFID of 1.44 at 256x256 and a state-of-the-art 1.52 at 512x512 with SiT-XL, while reducing token usage by up to 64x. These results confirm that masking and semantic guidance together prevent posterior collapse and achieve efficient, high-fidelity tokenization.