AGAN is the first neural architecture search method for GANs that discovers architectures outperforming state-of-the-art on CIFAR-10 unsupervised image generation and competitive on supervised tasks.
hub Mixed citations
Spectral Normalization for Generative Adversarial Networks
Mixed citation behavior. Most common role is background (60%).
48
Pith papers citing it
Background
60% of classified citations
abstract
One of the challenges in the study of generative adversarial networks is the instability of its training. In this paper, we propose a novel weight normalization technique called spectral normalization to stabilize the training of the discriminator. Our new normalization technique is computationally light and easy to incorporate into existing implementations. We tested the efficacy of spectral normalization on CIFAR10, STL-10, and ILSVRC2012 dataset, and we experimentally confirmed that spectrally normalized GANs (SN-GANs) is capable of generating images of better or equal quality relative to the previous training stabilization techniques.
hub tools
citation-role summary
background 3
method 2
citation-polarity summary
representative citing papers
RANs generalize moment unfolding to full phase-space unbinned unfolding via detector-level Wasserstein critics without requiring support overlap or multiple iterations.
cGAN surrogates recover 45-60% of CFD energy savings and high-velocity wake avoidance in 3D AUV path planning while running at 28-146 microsecond inference speeds across 19,800 trajectories.
Neural reconstruction losses in VAEs reduce latent information content and produce more isotropic latent geometries with even uncertainty distribution.
CAWI replaces standard random initialization of input-to-hidden weights in randomized neural networks with samples drawn from a data-fitted copula that preserves observed feature dependencies, yielding consistent accuracy gains on 83 classification benchmarks.
A CVAE-GAN U-Net stochastic generator trained on CloudSat-CALIPSO data halves RMSE in cloud histograms and cuts global shortwave cloud radiative effect bias by a factor of three versus the Räisänen method.
Scion is a new stochastic LMO-based optimizer family that unifies existing methods, supports unconstrained problems, and delivers hyperparameter transferability plus speedups on nanoGPT training.
Any maximally monotone operator can be approximated in local graph convergence by continuous encoder-decoder networks, with structure-preserving versions that retain maximal monotonicity via resolvent parameterizations.
ALU uses public data to suppress unlearning cost quadratically while characterizing distribution mismatch effects, enabling mass unlearning with maintained utility.
Semi-discrete Flow Matching produces terminal assignment regions that are topologically simple (open, simply connected, homeomorphic to the ball under assumption) yet geometrically distinct from optimal transport Laguerre cells, as they can be non-convex with curved boundaries.
A curvature penalty for KANs, derived to respect compositional effects and equipped with a proven upper bound on full-model curvature, produces smoother activations while preserving accuracy.
A modified DCGAN with an auxiliary discriminator using the membrane factor generates stable, previously unseen funicular shells optimized for pure compression in three dimensions.
Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.
HANNA is a thermodynamically consistent ML model for predicting excess Gibbs energy from molecular structures, trained on various binary mixture data and extended to multi-component mixtures using geometric projection.
A Tensor Train decomposition-based method enables efficient gradient-free activation maximization for neurons in spiking neural networks by searching generative model latent spaces.
Denoising Student distills the multi-step denoising process of score-based and diffusion models into a single forward pass, matching GAN sampling speed while producing comparable sample quality on CIFAR-10, CelebA, and 256x256 LSUN.
Subjective comparison of nine inpainting algorithms produces proposed objective metrics with high correlation to human perception of realism.
Dual-discriminator GAN with adversarial attention improves fine-grained medical image synthesis, especially in hard-to-generate tumor regions, and outperforms prior methods on brain tumor and CT-to-MRI tasks.
RED introduces pixel-wise mapping and zero-skipping dataflow for ReRAM deconvolution acceleration, reporting 1.15x-3.69x speedup and 8%-88.36% energy reduction versus prior ReRAM accelerators.
DASGAN trains a segmentation network on semi-automatically labeled CK images via unpaired translation to PD-L1, enabling epithelium segmentation and TC score estimation without serial sections.
A recurrent end-to-end network for exemplar-based video colorization that unifies semantic correspondence and color propagation with a temporal consistency loss.
Recursive generative retraining with heterogeneous rewards converges to a stable distribution satisfying a weighted Nash bargaining solution, preserving diversity under stated conditions.
AdamO modifies Adam with an orthogonality correction to ensure the spectral radius of the TD update operator stays below one, providing a theoretical stability guarantee for offline RL.
Pairing regularization mitigates intra-mode collapse in GANs by penalizing redundant latent-to-sample mappings, improving recall under collapse-prone conditions or precision under stabilized training.
citing papers explorer
-
Physics-informed, Generative Adversarial Design of Funicular Shells
A modified DCGAN with an auxiliary discriminator using the membrane factor generates stable, previously unseen funicular shells optimized for pure compression in three dimensions.
-
Diffusion Models Beat GANs on Image Synthesis
Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.