Goto

Collaborating Authors

86a1fa88adb5c33bd7a68ac2f9f3f96b-AuthorFeedback.pdf

Neural Information Processing Systems

REV3: We will clarify Tab.1 in the paper and add derivations of Eqs. 5, 6. DESIRE[21] is variational. The second is an online planning algorithm (Shooting), where Ego's future action sequences are38 optimized tomaximize fortheplanning rewardunderthelearned MFP dynamics model.










Augmentation-Aware Self-Supervision for Data-Efficient GAN Training

Neural Information Processing Systems

We further encourage the generator to adversarially learn from the self-supervised discriminator by generating augmentation-predictable real and not fake data.