Landscape Learning for Neural Network Inversion

Ruoshi Liu, Chengzhi Mao, Purva Tendulkar, Hao Wang, Carl Vondrick; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 2239-2250


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.

Related Material

[pdf] [arXiv]
@InProceedings{Liu_2023_ICCV, author = {Liu, Ruoshi and Mao, Chengzhi and Tendulkar, Purva and Wang, Hao and Vondrick, Carl}, title = {Landscape Learning for Neural Network Inversion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2239-2250} }