5 papers
SOL: Measuring Gaps between Text Distributions by Double Sliced Wasserstein Metrics
Gregor Kornhardt, Moritz Piening, Jannis Chemseddine +1
Evaluating text generation requires measuring how well the generated distribution matches the data distribution. For autoregressive models, this is done by the perplexity. Diffusio…
Spherical Flows for Sampling Categorical Data
Jannis Chemseddine, Gregor Kornhardt, Gabriele Steidl
We study the problem of learning generative models for discrete sequences in a continuous embedding space. Whereas prior approaches typically operate in Euclidean space or on the p…
HOT-POT: Optimal Transport for Sparse Stereo Matching
Antonin Clerc, Michael Quellmalz, Moritz Piening +3
Stereo vision between images faces a range of challenges, including occlusions, motion, and camera distortions, across applications in autonomous driving, robotics, and face analys…
Adapting Noise to Data: Generative Flows from 1D Processes
Jannis Chemseddine, Gregor Kornhardt, Richard Duong +1
The default Gaussian latent in flow-based generative models poses challenges when learning certain distributions such as heavy-tailed ones. We introduce a general framework for lea…
Solving Inverse Problems with Conditional-GAN Prior via Fast Network-Projected Gradient Descent
Muhammad Fadli Damara, Gregor Kornhardt, Peter Jung
The projected gradient descent (PGD) method has shown to be effective in recovering compressed signals described in a data-driven way by a generative model, i.e., a generator which…