MetricOpt: Learning to Optimize Black-Box Evaluation Metrics
Backpropagate through your non-differentiable metric function
#optimization
#loss-function
#gradient-descent
Gradient Matching for Domain Generalization
Guiding neural networks to generalize across unseen data domains
#generalization
#loss-function
#gradient-descent
Surrogate Gradient Field for Latent Space Manipulation
Manipulate images by exploring paths in the GAN latent space with geometric understanding
#generative-adversarial-network
#image-manipulation
#gradient-descent