Papers › Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules

Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules

14 May 2019arXiv:1905.05393archive 2025-07-28

Daniel Ho, Eric Liang, Ion Stoica, Pieter Abbeel, Xi Chen

A key challenge in leveraging data augmentation for neural network training is choosing an effective augmentation policy from a large search space of candidate operations. Properly chosen augmentation policies can lead to significant generalization improvements; however, state-of-the-art approaches such as AutoAugment are computationally infeasible to run for the ordinary user. In this paper, we introduce a new data augmentation algorithm, Population Based Augmentation (PBA), which generates nonstationary augmentation policy schedules instead of a fixed augmentation policy. We show that PBA can match the performance of AutoAugment on CIFAR-10, CIFAR-100, and SVHN, with three orders of magnitude less overall compute. On CIFAR-10 we achieve a mean test error of 1.46%, which is a slight improvement upon the current state-of-the-art. The code for PBA is open source and is available at https://github.com/arcelien/pba.

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="1905.05393")

Code

Syntology Ran 0 of 18 code samples harvested from 2 repositories linked to this paper; 18 have no recorded run.

By repository: official repository: 17 samples from 1 repository, 0 ran; community (archive-listed): 1 sample 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.

arcelien/pba officialmentioned in papermentioned on GitHubtfApache-2.0 report
Zhiwei-Z/pba_experiment mentioned on GitHubtfApache-2.0 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

18 samples harvested; 0 ran; 0 honoured the contract we drafted; 18 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.

18unverified

Licence: 18 of the 18 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

apply_policy arcelien/pba/pba/augmentation_transforms.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 36fd5169c16678b5 · report
conv2d_fixed_padding arcelien/pba/pba/resnet.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 09f6f950522b2929 · report
create_cutout_mask arcelien/pba/autoaugment/augmentation_transforms.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · a7723bf702941670 · report
eval_child_model arcelien/pba/pba/helper_utils.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · e07180040df49662 · report
fixed_padding arcelien/pba/pba/resnet.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · c2b850137a837e22 · report
global_avg_pool arcelien/pba/autoaugment/custom_ops.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 17411729594afb42 · report
parse_log arcelien/pba/pba/utils.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 363604d5223dc581 · report
parse_log_schedule arcelien/pba/pba/utils.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 9e961b28ac45f45c · report
parse_policy arcelien/pba/pba/data_utils.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · a462e307b7fef357 · report
pil_unwrap arcelien/pba/pba/augmentation_transforms.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 847b897e7843bacf · report
pil_wrap arcelien/pba/pba/augmentation_transforms.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 24a49b2f64553568 · report
random_flip arcelien/pba/autoaugment/augmentation_transforms.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 6e1198a9c8c47438 · report
shuffle_data arcelien/pba/pba/data_utils.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 9da9105a07289a15 · report
step_lr arcelien/pba/pba/helper_utils.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 69e94358fb4b69c7 · report
variable arcelien/pba/autoaugment/custom_ops.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · f6b18b79eccd8391 · report
zero_pad arcelien/pba/autoaugment/custom_ops.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 563e25e514f4a2a6 · report
zero_pad_and_crop arcelien/pba/autoaugment/augmentation_transforms.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · f3f5fce61e36ad06 · report
batch_norm Zhiwei-Z/pba_experiment/pba/resnet.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · f4fba27e3fd641f2 · report

Tasks

Data AugmentationImage Augmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification SVHN PBA [ho2019pba] Percentage error 1.2 #4 of 62 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

Introduced by this paper: Population Based Augmentation

AutoAugmentLSTMPopulation Based AugmentationPopulation Based TrainingSigmoid ActivationTanh Activation

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