MANGO通过分组算子学习解耦的图像变换，训练速度提升100倍。
MANGO: Learning Disentangled Image Transformation Manifolds with Grouped Operators
- 用分组算子在不同隐空间学习解耦的图像变换
- 实现变换组合且训练速度比之前快100倍
- 可自定义目标变换，提升语义可解释性
直接从样本中学习语义明确的图像变换（如旋转、粗细、模糊）是一项挑战。近期的流形自编码器（MAE）使用一组李群算子从样本中学习图像变换，但其算子无法保证解耦，且模型扩展时训练成本过高。为此，我们提出MANGO（带分组算子的变换流形），用于在不同隐子空间中学习解耦的变换算子。该方法允许使用者定义希望建模的变换类型，从而增强算子的语义意义。实验表明，MANGO支持变换组合，并采用单阶段训练流程，相比之前方法实现100倍加速。
原文摘要 · Abstract (English)
Learning semantically meaningful image transformations (i.e. rotation, thickness, blur) directly from examples can be a challenging task. Recently, the Manifold Autoencoder (MAE) proposed using a set of Lie group operators to learn image transformations directly from examples. However, this approach has limitations, as the learned operators are not guaranteed to be disentangled and the training routine is prohibitively expensive when scaling up the model. To address these limitations, we propose MANGO (transformation Manifolds with Grouped Operators) for learning disentangled operators that describe image transformations in distinct latent subspaces. Moreover, our approach allows practitioners the ability to define which transformations they aim to model, thus improving the semantic meaning of the learned operators. Through our experiments, we demonstrate that MANGO enables composition of image transformations and introduces a one-phase training routine that leads to a 100x speedup over prior works.
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。