TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/BigGAN

BigGAN

Computer VisionIntroduced 2000103 papers
Source Paper

Description

BigGAN is a type of generative adversarial network that was designed for scaling generation to high-resolution, high-fidelity images. It includes a number of incremental changes and innovations. The baseline and incremental changes are:

  • Using SAGAN as a baseline with spectral norm. for G and D, and using TTUR.
  • Using a Hinge Loss GAN objective
  • Using class-conditional batch normalization to provide class information to G (but with linear projection not MLP.
  • Using a projection discriminator for D to provide class information to D.
  • Evaluating with EWMA of G's weights, similar to ProGANs.

The innovations are:

  • Increasing batch sizes, which has a big effect on the Inception Score of the model.
  • Increasing the width in each layer leads to a further Inception Score improvement.
  • Adding skip connections from the latent variable zzz to further layers helps performance.
  • A new variant of Orthogonal Regularization.

Papers Using This Method

ParaGAN: A Scalable Distributed Training Framework for Generative Adversarial Networks2024-11-06Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization2024-10-27On quantifying and improving realism of images generated with diffusion2023-09-26Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows2023-09-21A Strategic Framework for Optimal Decisions in Football 1-vs-1 Shot-Taking Situations: An Integrated Approach of Machine Learning, Theory-Based Modeling, and Game Theory2023-07-27Pyrus Base: An Open Source Python Framework for the RoboCup 2D Soccer Simulation2023-07-22Diffusion Models Beat GANs on Image Classification2023-07-17Diversity is Strength: Mastering Football Full Game with Interactive Reinforcement Learning of Multiple AIs2023-06-28Rosetta Neurons: Mining the Common Units in a Model Zoo2023-06-15Toward more accurate and generalizable brain deformation estimators for traumatic brain injury detection with unsupervised domain adaptation2023-06-08FOOCTTS: Generating Arabic Speech with Acoustic Environment for Football Commentator2023-06-07Action valuation of on- and off-ball soccer players based on multi-agent deep reinforcement learning2023-05-29Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?2023-05-27Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrations2023-05-22An Empirical Study on Google Research Football Multi-agent Scenarios2023-05-16The MuSe 2023 Multimodal Sentiment Analysis Challenge: Mimicked Emotions, Cross-Cultural Humour, and Personalisation2023-05-05TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation2023-04-26SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes2023-04-11VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views2023-04-10Towards Active Learning for Action Spotting in Association Football Videos2023-04-09