Asia
Supplementary Material for Cross-modal Active Complementary Learning with Self-refining CorrespondenceY ang Qin 1, Yuan Sun
For all parameter settings, see Appendix B.2. The code of our CRCL will be released on GitHub.
Cross-modalActiveComplementaryLearning withSelf-refiningCorrespondence
These works attempt to leverage the memorization effect of DNNs [25] to gradually distinguish the noisy image-text pairs for robust learning in a co-teaching manner.
Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness
Fanny Yang, Zuowen Wang, Christina Heinze-Deml
Neural Information Processing Systems http://nips.cc/
IsBang-BangControlAllYouNeed? SolvingContinuousControlwithBernoulliPolicies
Real-world robotics tasks commonly manifest ascontrol problems overcontinuous action spaces. When learning to act in such settings, control policies are typically represented as continuous probability distributions that cover all feasible control inputs - often Gaussians. The underlying assumption is that this enables more refined decisions compared to crude policy choices such as discretized controllers, which limit the search space but induce abrupt changes. While switching controls canbeundesirable inpractice astheymaychallenge stability andaccelerate system weardown, they are theoretically feasible and even arise as optimal strategies in some settings.
UFC-BERT: UnifyingMulti-ModalControlsfor ConditionalImageSynthesis
Conditional image synthesis aims tocreate an image according tothe given control signals.