Search Results for author:
Found 8 papers, 1 papers with code
Backdoor Attack with Mode Mixture Latent Modification
Backdoor attacks become a significant security concern for deep neural networks in recent years.
Learning for Transductive Threshold Calibration in Open-World Recognition
In deep metric learning for visual recognition, the calibration of distance thresholds is crucial for achieving desired model performance in the true positive rates (TPR) or true negative rates (TNR).
Learning Deep Latent Variable Models by Short-Run MCMC Inference With Optimal Transport Correction
Learning latent variable models with deep top-down architectures typically requires inferring the latent variables for each training example based on the posterior distribution of these latent variables.
Efficient Optimal Transport Algorithm by Accelerated Gradient descent
Basically, the non-smooth c-transform of the Kantorovich potential is approximated by the smooth Log-Sum-Exp function, which finally smooths the original non-smooth Kantorovich dual functional (energy).
AE-OT: A NEW GENERATIVE MODEL BASED ON EXTENDED SEMI-DISCRETE OPTIMAL TRANSPORT
In order to tackle the both problems, we explicitly separate the manifold embedding and the optimal transportation; the first part is carried out using an autoencoder to map the images onto the latent space; the second part is accomplished using a GPU-based convex optimization to find the discontinuous transportation maps.
AE-OT-GAN: Training GANs from data specific latent distribution
Though generative adversarial networks (GANs) areprominent models to generate realistic and crisp images, they often encounter the mode collapse problems and arehard to train, which comes from approximating the intrinsicdiscontinuous distribution transform map with continuousDNNs.
Mode Collapse and Regularity of Optimal Transportation Maps
This work builds the connection between the regularity theory of optimal transportation map, Monge-Amp\`{e}re equation and GANs, which gives a theoretic understanding of the major drawbacks of GANs: convergence difficulty and mode collapse.
Fast and High Quality Highlight Removal from A Single Image
Specifically, this paper derives a normalized dichromatic model for the pixels with identical diffuse color: a unit circle equation of projection coefficients in two subspaces that are orthogonal to and parallel with the illumination, respectively.
