提出可用户控制的图像逆投影方法，实现更丰富的高维数据生成。
LCIP: Loss-Controlled Inverse Projection of High-Dimensional Image Data
- 通过用户参数控制，动态扫过数据空间生成新样本
- 突破传统方法仅能生成固定曲面的限制，覆盖更广数据分布
- 适用于任意降维方法和数据集，尤其适合图像风格迁移
投影方法 $P$ 将高维数据映射到二维散点图以支持可视化探索。逆投影方法 $P^{-1}$ 则将二维空间映射回数据空间，用于数据增强、分类器分析和数据补全等任务。现有 $P^{-1}$ 方法存在根本局限：只能在数据空间中生成固定的表面结构，难以覆盖空间的丰富性。本文提出一种新方法，可在用户控制下‘扫过’数据空间。该方法对任意 $P$ 技术和数据集均适用，仅需两个直观的用户设定参数，实现简单。我们通过图像风格迁移的广泛应用展示了其效果。
原文摘要 · Abstract (English)
Projections (or dimensionality reduction) methods $P$ aim to map high-dimensional data to typically 2D scatterplots for visual exploration. Inverse projection methods $P^{-1}$ aim to map this 2D space to the data space to support tasks such as data augmentation, classifier analysis, and data imputation. Current $P^{-1}$ methods suffer from a fundamental limitation -- they can only generate a fixed surface-like structure in data space, which poorly covers the richness of this space. We address this by a new method that can `sweep' the data space under user control. Our method works generically for any $P$ technique and dataset, is controlled by two intuitive user-set parameters, and is simple to implement. We demonstrate it by an extensive application involving image manipulation for style transfer.
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。