用通道当像素令牌，快且省资源地生成可变长度图像表示
ChannelTok: Efficient Flexible-Length Vision Tokenization
- 把每个特征通道视为一个视觉令牌，实现轻量级混合模型
- 推理时保留前k个通道即可灵活压缩，解码速度提升8.6倍
- 适合需要高效生成的场景，如移动端视觉任务
主流灵活视觉令牌化方法虽达到顶尖质量，但依赖参数庞大的主干网络和缓慢的多步生成解码器。本文摒弃复杂的空间令牌范式，提出一种简单、轻量、快速的通道级灵活长度令牌化方法。将每个潜在通道视为视觉令牌，实现参数高效的CNN-Transformer混合主干网络。训练中采用随机尾部丢弃策略，自然促使通道按语义重要性排序，推理时仅需保留前k个通道即可实现灵活压缩，并天然支持可变长度自回归图像生成。在ImageNet上的大量实验表明，该方法在多种令牌预算下均保持稳定质量。结果确立了新的质量-效率前沿：模型在感知质量上达到最优（rFID 2.92），解码速度比次优方案快8.6倍，参数量更小2.1倍（159M）。
原文摘要 · Abstract (English)
Leading flexible vision tokenizers achieve SOTA quality at an extreme cost, relying on parameter-heavy backbones and slow, multi-step generative decoders. We depart from this complex, spatial-token paradigm and introduce a simple, lightweight, and fast channel-wise flexible-length tokenizer. Our method treats each latent channel as a visual token, enabling a parameter-efficient CNN-Transformer hybrid backbone. Furthermore, employing a stochastic tail-dropping paradigm during training naturally forces channels to organize by semantic importance. This allows for flexible compression at inference by simply retaining the first $k$ channels, and naturally enables variable-length autoregressive image generation. We validate our approach through extensive experiments on ImageNet, demonstrating consistent quality across diverse token budgets. The results establish a new quality-efficiency frontier: our model achieves state-of-the-art perceptual quality (rFID 2.92) while being $8.6\times$ faster in decoding and $2.1\times$ smaller (159M params) than the next-best alternative. Our work establishes channel-wise tokenization as a powerful and practical paradigm for efficient visual representation. Project page: https://channeltok.github.io
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。