Papers › Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization

Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization

14 Nov 2018arXiv:1811.05850archive 2025-07-28

Senwei Liang, Yuehaw Khoo, Haizhao Yang

Overfitting frequently occurs in deep learning. In this paper, we propose a novel regularization method called Drop-Activation to reduce overfitting and improve generalization. The key idea is to drop nonlinear activation functions by setting them to be identity functions randomly during training time. During testing, we use a deterministic network with a new activation function to encode the average effect of dropping activations randomly. Our theoretical analyses support the regularization effect of Drop-Activation as implicit parameter reduction and verify its capability to be used together with Batch Normalization (Ioffe and Szegedy 2015). The experimental results on CIFAR-10, CIFAR-100, SVHN, EMNIST, and ImageNet show that Drop-Activation generally improves the performance of popular neural network architectures for the image classification task. Furthermore, as a regularizer Drop-Activation can be used in harmony with standard training and regularization techniques such as Batch Normalization and Auto Augment (Cubuk et al. 2019). The code is available at \url{https://github.com/LeungSamWai/Drop-Activation}.

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="1811.05850")

Code

Syntology Ran 1 of 8 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 8 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

LeungSamWai/Drop-Activation officialmentioned in papermentioned on GitHubpytorchMIT report
statsu1990/drop-activation mentioned 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

8 samples harvested; 1 ran; 0 honoured the contract we drafted; 7 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.

1ran · our draft was wrong
7unverified

Licence: 0 of the 8 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 LeungSamWai/Drop-Activation. “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.

plot_overlap LeungSamWai/Drop-Activation/utils/logger.py official repository ran · our draft was wrong MIT (permissive) · 50afa2863ffd9fde · report
colorize LeungSamWai/Drop-Activation/utils/visualize.py official repository unverified MIT (permissive) · c87e7665fde6cdfc · report
gauss LeungSamWai/Drop-Activation/utils/visualize.py official repository unverified MIT (permissive) · d66f0a3cbb86204c · report
get_mean_and_std LeungSamWai/Drop-Activation/utils/misc.py official repository unverified MIT (permissive) · 1d6e2edb8832d7b0 · report
make_image LeungSamWai/Drop-Activation/utils/visualize.py official repository unverified MIT (permissive) · 1394422d51c4b126 · report
resnext101 LeungSamWai/Drop-Activation/models/imagenet/resnext.py official repository unverified MIT (permissive) · 6db40ac24bfe6958 · report
resnext152 LeungSamWai/Drop-Activation/models/imagenet/resnext.py official repository unverified MIT (permissive) · 9e4382fd1664da47 · report
resnext50 LeungSamWai/Drop-Activation/models/imagenet/resnext.py official repository unverified MIT (permissive) · 8032831473a4283c · report

Tasks

Image Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification SVHN Drop-Activation Percentage error 1.46 #9 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

Batch Normalization

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