Search Results for author:
Found 11 papers, 2 papers with code
Compress Polyphone Pronunciation Prediction Model with Shared Labels
In contrast to existing quantization with low precision data format and projection layer, we propose a novel method based on shared labels, which focuses on compressing the fully-connected layer before Softmax for models with a huge number of labels in TTS polyphone selection.
Let Real Images be as a Judger, Spotting Fake Images Synthesized with Generative Models
Unfortunately, the artifact patterns in fake images synthesized by different generative models are inconsistent, leading to the failure of previous research that relied on spotting subtle differences between real and fake.
What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Network
In recent decades, Generative Adversarial Network (GAN) and its variants have achieved unprecedented success in image synthesis.
What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networks
In recent decades, Generative Adversarial Network (GAN) and its variants have achieved unprecedented success in image synthesis.
Collaborative Learning in General Graphs with Limited Memorization: Complexity, Learnability, and Reliability
The efficacy of our proposed three-staged collaborative learning algorithm is finally verified by extensive experiments on both synthetic and real datasets.
Hiding Data in Colors: Secure and Lossless Deep Image Steganography via Conditional Invertible Neural Networks
Deep image steganography is a data hiding technology that conceal data in digital images via deep neural networks.
Generalized Local Optimality for Video Steganalysis in Motion Vector Domain
So we generalize the local optimality from the MV domain to the PMV domain.
Analyzing Adversarial Robustness of Deep Neural Networks in Pixel Space: a Semantic Perspective
Previous works study the adversarial robustness of image classifiers on image level and use all the pixel information in an image indiscriminately, lacking of exploration of regions with different semantic meanings in the pixel space of an image.
Using contrastive learning to improve the performance of steganalysis schemes
To decrease the computing complexity of the contrastive loss in supervised learning, we design a novel Steganalysis Contrastive Loss (StegCL) based on the equivalence and transitivity of similarity.
Combination of window-sliding and prediction range method based on LSTM model for predicting cryptocurrency
The present study aims to establish the model of the cryptocurrency price trend based on financial theory using the LSTM model with multiple combinations between the window length and the predicting horizons, the random walk model is also applied with different parameter settings.
Towards a Robust Deep Neural Network in Texts: A Survey
Recently, studies have revealed adversarial examples in the text domain, which could effectively evade various DNN-based text analyzers and further bring the threats of the proliferation of disinformation.
