Papers › Mish: A Self Regularized Non-Monotonic Activation Function

Mish: A Self Regularized Non-Monotonic Activation Function

23 Aug 2019BMVC 2020 8arXiv:1908.08681archive 2025-07-28

Diganta Misra

We propose Mish, a novel self-regularized non-monotonic activation function which can be mathematically defined as: f(x)=xtanh(softplus(x)). As activation functions play a crucial role in the performance and training dynamics in neural networks, we validated experimentally on several well-known benchmarks against the best combinations of architectures and activation functions. We also observe that data augmentation techniques have a favorable effect on benchmarks like ImageNet-1k and MS-COCO across multiple architectures. For example, Mish outperformed Leaky ReLU on YOLOv4 with a CSP-DarkNet-53 backbone on average precision (AP₅₀ᵛᵃˡ) by 2.1% in MS-COCO object detection and ReLU on ResNet-50 on ImageNet-1k in Top-1 accuracy by ≈1% while keeping all other network parameters and hyperparameters constant. Furthermore, we explore the mathematical formulation of Mish in relation with the Swish family of functions and propose an intuitive understanding on how the first derivative behavior may be acting as a regularizer helping the optimization of deep neural networks. Code is publicly available at https://github.com/digantamisra98/Mish.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="1908.08681")

Code

Syntology Ran 4 of 12 code samples harvested from 2 repositories linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 1 ran; community (archive-listed): 3 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

digantamisra98/Mish officialmentioned in papermentioned on GitHubpytorchMIT report
LeeGitaek/Kaggle_Solving mentioned on GitHubGPL-3.0 report
tyunist/memory_efficient_mish_swish mentioned on GitHubpytorch report
lessw2020/mish pytorchApache-2.0 report
tensorflow/addons tfApache-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

12 samples harvested; 4 ran; 1 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
2ran
8unverified

Licence: 0 of the 12 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.

mish digantamisra98/Mish/Mish/Torch/functional.py official repository ran MIT (permissive) · e8af53cde1de7240 · report
accuracy digantamisra98/Mish/exps/train_cifar.py official repository unverified MIT (permissive) · f0c9a29156911331 · report
build_model digantamisra98/Mish/exps/op_landscape.py official repository unverified MIT (permissive) · 09134815082c4723 · report
convert_to_PIL digantamisra98/Mish/exps/op_landscape.py official repository unverified MIT (permissive) · 90dcca0cc0384d13 · report
mish digantamisra98/Mish/Mish/TFKeras/mish.py official repository unverified MIT (permissive) · 77350704c0889a70 · report
resnet20 digantamisra98/Mish/exps/resnet.py official repository unverified MIT (permissive) · fe525ef6a5d1473a · report
resnet32 digantamisra98/Mish/exps/resnet.py official repository unverified MIT (permissive) · 278ef88735703a97 · report
resnet44 digantamisra98/Mish/exps/resnet.py official repository unverified MIT (permissive) · 6d73f5ab551aef6b · report
validate digantamisra98/Mish/exps/train_cifar.py official repository unverified MIT (permissive) · 2c3ebef98e7b5f52 · report
conv lessw2020/mish/mxresnet.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · c9a6012d7fbd67dd · report
conv_layer lessw2020/mish/mxresnet.py community (archive-listed) ran Apache-2.0 (permissive) · 737c7df8da0c198b · report
noop lessw2020/mish/mxresnet.py community (archive-listed) ran · honoured contract fingerprinted Apache-2.0 (permissive) · 5e2ed23acb71ee11 · report

Tasks

Image ClassificationObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 ResNet 9 + Mish Percentage correct 94.05 #164 of 265 Archive leaderboard report
Image Classification CIFAR-10 ResNet v2-20 (Mish activation) Percentage correct 92.02 #186 of 265 Archive leaderboard report
Image Classification CIFAR-100 ResNet v2-110 (Mish activation) Percentage correct 74.41 #154 of 211 Archive leaderboard report
Image Classification ImageNet CSPResNeXt-50 + Mish Top 1 Accuracy 79.8% #735 of 1060 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockChannel ShuffleConcatenated Skip ConnectionConvolutionCosine AnnealingDense BlockDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutFire ModuleGlobal Average PoolingGrouped ConvolutionKaiming InitializationL1 RegularizationMax PoolingMixupMobileNetV1NADAMPointwise ConvolutionReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionShuffleNet V2 BlockShuffleNet V2 Downsampling BlockShuffleNet v2Sigmoid ActivationSimpleNetSoftmaxSqueeze-and-Excitation BlockSqueezeNetTanh ActivationWeight DecayWide Residual BlockWideResNetXavier Initialization

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