论文标题
神经网络反演的景观学习
Landscape Learning for Neural Network Inversion
论文作者
论文摘要
许多机器学习方法通过在推理时反转神经网络来运行，这已成为解决计算机视觉，机器人技术和图形中反向问题的流行技术。但是，这些方法通常涉及通过高度非凸损失景观的梯度下降，从而导致优化过程不稳定和缓慢。我们介绍了一种学习损失景观的方法，其中梯度下降是有效的，从而为反转过程带来了巨大的改进和加速。我们在许多生成和判别任务的方法上证明了这一优势，包括GAN倒置，对抗防御和3D人类姿势重建。
Many machine learning methods operate by inverting a neural network at inference time, which has become a popular technique for solving inverse problems in computer vision, robotics, and graphics. However, these methods often involve gradient descent through a highly non-convex loss landscape, causing the optimization process to be unstable and slow. We introduce a method that learns a loss landscape where gradient descent is efficient, bringing massive improvement and acceleration to the inversion process. We demonstrate this advantage on a number of methods for both generative and discriminative tasks, including GAN inversion, adversarial defense, and 3D human pose reconstruction.
