Fréchet distance
PulseAugur coverage of Fréchet distance — every cluster mentioning Fréchet distance across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New AdvFD method boosts visual generation by adapting Fréchet distance
Researchers have introduced Adversarial Fréchet Distance (AdvFD), a novel method to enhance visual generation models. AdvFD addresses the issue of "Fréchet hacking" by incorporating a learnable adversarial representatio…
-
New terminal embeddings advance time-series dimension reduction
Researchers have developed a novel generalization of terminal embeddings to affine line-segments, enabling dimension reduction for time-series data. This advancement allows for the creation of dimension-free coresets fo…
-
New method simplifies dimension reduction for curves and surfaces
Researchers have developed a simplified and generalized method for dimension reduction of high-dimensional polygonal curves. This new approach utilizes sparse oblivious subspace embeddings to provide a more straightforw…
-
AI Research: Image encoding naturalness predicts but doesn't cause transferability
Researchers have investigated the relationship between the visual naturalness of images generated from one-dimensional data streams and their transferability to vision backbones. Their study, using the WorldStream corpu…
-
Researchers propose FD-loss to optimize visual generation in representation space
Researchers have introduced a new training objective called FD-loss, which optimizes the Fréchet Distance (FD) in representation spaces for visual generation. This method decouples the population size for FD estimation …