FD-loss
PulseAugur coverage of FD-loss — every cluster mentioning FD-loss across labs, papers, and developer communities, ranked by signal.
4 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 FD-loss technique improves autoregressive image generation quality
Researchers have developed a new post-training technique called Fréchet Distributional Post-Training (FD-loss) for autoregressive image generators. This method addresses the mismatch between token-level cross-entropy pr…
-
New Amortized Moment Matching technique enhances visual generation models
Researchers have introduced Amortized Moment Matching (AMM), a novel technique that uses neural networks to learn distributional training signals from data moments. This method, instantiated as the Amortized Fréchet Dis…
-
Fréchet Distance Loss Enhances Medical Image Generation
Researchers have developed a new method to improve the generation of synthetic medical images using diffusion models. The proposed Fréchet Distance loss (FD-loss) technique fine-tunes these models by aligning statistica…
-
OpenAI-affiliated researchers integrate FID into training, achieving sub-0.8 ImageNet scores
Researchers from USC, CMU, CUHK, and OpenAI have developed a new method called FD-loss that allows the Fréchet Inception Distance (FID) metric to be directly incorporated into the training process of image generation mo…
-
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 …