Search Results for author:
Found 8 papers, 0 papers with code
AutoMix: Mixup Networks for Sample Interpolation via Cooperative Barycenter Learning
This paper proposes new ways of sample mixing by thinking of the process as generation of barycenter in a metric space for data augmentation.
The Sogou-TIIC Speech Translation System for IWSLT 2018
Our final average result on speech translation is 31. 02 BLEU.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Double-Bounded Optimal Transport for Advanced Clustering and Classification
Even with vanilla Softmax trained features, our extensive experimental results show that our method can achieve good results with our improved inference scheme in the testing stage.
On the Expressiveness, Predictability and Interpretability of Neural Temporal Point Processes
Despite the fast advance in neural temporal point processes (NTPP) which enjoys high model capacity, there are still some standing gaps to fill including model expressiveness, predictability, and interpretability, especially with the wide application of event sequence modeling.
Improving Generative Adversarial Networks via Adversarial Learning in Latent Space
Although many efforts have been made in terms of backbone architecture design, loss function, and training techniques, few results have been obtained on how the sampling in latent space can affect the final performance, and existing works on latent space mainly focus on controllability.
Adversarial Robustness via Adaptive Label Smoothing
We first show both theoretically and empirically that strong smoothing in AT increases local smoothness of the loss surface which is beneficial for robustness but sacrifices the training loss which influences the accuracy of samples near the decision boundary.
IID-GAN: an IID Sampling Perspective for Regularizing Mode Collapse
Based on this observation, considering a necessary condition of IID generation that the inverse samples from target data should also be IID in the source distribution, we propose a new loss to encourage the closeness between inverse samples of real data and the Gaussian source in latent space to regularize the generation to be IID from the target distribution.
InvertGAN: Reducing mode collapse with multi-dimensional Gaussian Inversion
Generative adversarial networks have shown their ability in capturing high-dimensional complex distributions and generating realistic data samples e. g. images.
