Papers › Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of...

Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN

22 Nov 2018arXiv:1811.09245archive 2025-07-28

Masaki Saito, Shunta Saito, Masanori Koyama, Sosuke Kobayashi

Training of Generative Adversarial Network (GAN) on a video dataset is a challenge because of the sheer size of the dataset and the complexity of each observation. In general, the computational cost of training GAN scales exponentially with the resolution. In this study, we present a novel memory efficient method of unsupervised learning of high-resolution video dataset whose computational cost scales only linearly with the resolution. We achieve this by designing the generator model as a stack of small sub-generators and training the model in a specific way. We train each sub-generator with its own specific discriminator. At the time of the training, we introduce between each pair of consecutive sub-generators an auxiliary subsampling layer that reduces the frame-rate by a certain ratio. This procedure can allow each sub-generator to learn the distribution of the video at different levels of resolution. We also need only a few GPUs to train a highly complex generator that far outperforms the predecessor in terms of inception scores.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1811.09245")

Code

Syntology Ran 0 of 6 code samples harvested from 1 repository linked to this paper; 6 have no recorded run.

By repository: official repository: 6 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

pfnet-research/tgan2 officialmentioned in papermentioned on GitHubMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

6 samples harvested; 0 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

6unverified

Licence: 0 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from pfnet-research/tgan2. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

init_logger pfnet-research/tgan2/tgan2/datasets/motion_jpeg.py official repository unverified MIT (permissive) · 38401635d6be718f · report
make_config pfnet-research/tgan2/tgan2/utils.py official repository unverified MIT (permissive) · 550ecc473bd99ad0 · report
make_frame pfnet-research/tgan2/tgan2/datasets/motion_jpeg.py official repository unverified MIT (permissive) · 66377a4582ab9255 · report
make_instance pfnet-research/tgan2/tgan2/utils.py official repository unverified MIT (permissive) · cd696a1b5338b469 · report
pooling pfnet-research/tgan2/tgan2/datasets/multi_level.py official repository unverified MIT (permissive) · 8a91291b41bbb98e · report
subsample pfnet-research/tgan2/tgan2/datasets/multi_level.py official repository unverified MIT (permissive) · 932dd8314fd7500b · report

Tasks

Video Generation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Generation UCF-101 16 frames, 128x128, Unconditional TGANv2 (2020) Inception Score 28.87 #1 of 6 Archive leaderboard report
Video Generation UCF-101 16 frames, 128x128, Unconditional TGANv2 Inception Score 24.34 #4 of 6 Archive leaderboard report
Video Generation UCF-101 16 frames, Unconditional, Single GPU TGANv2 Inception Score 21.45 #2 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections