{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mish-a-self-regularized-non-monotonic-neural","title":"Mish: A Self Regularized Non-Monotonic Activation Function","arxiv_id":"1908.08681","date":"2019-08-23","proceeding":"BMVC 2020 8","authors":["Diganta Misra"],"abstract":"We propose $\\textit{Mish}$, a novel self-regularized non-monotonic activation function which can be mathematically defined as: $f(x)=x\\tanh(softplus(x))$. 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 ($AP_{50}^{val}$) by 2.1$\\%$ in MS-COCO object detection and ReLU on ResNet-50 on ImageNet-1k in Top-1 accuracy by $\\approx$1$\\%$ 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.","url_abs":"https://arxiv.org/abs/1908.08681v3","url_pdf":"https://arxiv.org/pdf/1908.08681v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mish-a-self-regularized-non-monotonic-neural","repo_url":"https://github.com/digantamisra98/Mish","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mish-a-self-regularized-non-monotonic-neural","repo_url":"https://github.com/LeeGitaek/Kaggle_Solving","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"mish-a-self-regularized-non-monotonic-neural","repo_url":"https://github.com/tyunist/memory_efficient_mish_swish","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mish-a-self-regularized-non-monotonic-neural","repo_url":"https://github.com/Andy-Dang12/Activation-Functions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mish-a-self-regularized-non-monotonic-neural","repo_url":"https://github.com/DucQuan12/Classification-with-activation-mish","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"mish-a-self-regularized-non-monotonic-neural","repo_url":"https://github.com/lessw2020/mish","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mish-a-self-regularized-non-monotonic-neural","repo_url":"https://github.com/pavansai26/mish-activation-function-implementation-from-scratch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"mish-a-self-regularized-non-monotonic-neural","repo_url":"https://github.com/tensorflow/addons","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mish-a-self-regularized-non-monotonic-neural","repo_url":"https://github.com/thomasbrandon/mish-cuda","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"channel-shuffle","method_name":"Channel Shuffle"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"fire-module","method_name":"Fire Module"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"l1-regularization","method_name":"L1 Regularization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"mixup","method_name":"Mixup"},{"method_slug":"mobilenetv1","method_name":"MobileNetV1"},{"method_slug":"nadam","method_name":"NADAM"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"resnext","method_name":"ResNeXt"},{"method_slug":"resnext-block","method_name":"ResNeXt Block"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"shufflenet-v2-block","method_name":"ShuffleNet V2 Block"},{"method_slug":"shufflenet-v2-downsampling-block","method_name":"ShuffleNet V2 Downsampling Block"},{"method_slug":"shufflenet-v2","method_name":"ShuffleNet v2"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"simplenet","method_name":"SimpleNet"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"squeeze-and-excitation-block","method_name":"Squeeze-and-Excitation Block"},{"method_slug":"squeezenet","method_name":"SqueezeNet"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wide-residual-block","method_name":"Wide Residual Block"},{"method_slug":"wideresnet","method_name":"WideResNet"},{"method_slug":"xavier-initialization","method_name":"Xavier Initialization"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ResNet 9 + Mish","rank_in_archive_order":164,"of":265,"metrics":{"Percentage correct":"94.05"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ResNet v2-20 (Mish activation)","rank_in_archive_order":186,"of":265,"metrics":{"Percentage correct":"92.02"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"ResNet v2-110 (Mish activation)","rank_in_archive_order":154,"of":211,"metrics":{"Percentage correct":"74.41"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CSPResNeXt-50 + Mish","rank_in_archive_order":735,"of":1060,"metrics":{"Top 1 Accuracy":"79.8%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1908.08681","atlas_url":"https://app.syntology.ai/?focus=1908.08681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.08681"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/addons","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Andy-Dang12/Activation-Functions","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/digantamisra98/Mish","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pavansai26/mish-activation-function-implementation-from-scratch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DucQuan12/Classification-with-activation-mish","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LeeGitaek/Kaggle_Solving","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tyunist/memory_efficient_mish_swish","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thomasbrandon/mish-cuda","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lessw2020/mish","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"ran":2,"ran_honours":1,"unverified":8},"by_repo_kind":{"official":{"samples":9,"ran":1,"repositories":1},"listed":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c9a6012d7fbd67dd","entry":"conv","repo":"lessw2020/mish","repo_kind":"listed","path":"mxresnet.py","file_url":"https://github.com/lessw2020/mish/blob/HEAD/mxresnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c9a6012d7fbd67dd"}},{"code_sha256_prefix":"737c7df8da0c198b","entry":"conv_layer","repo":"lessw2020/mish","repo_kind":"listed","path":"mxresnet.py","file_url":"https://github.com/lessw2020/mish/blob/HEAD/mxresnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"737c7df8da0c198b"}},{"code_sha256_prefix":"e8af53cde1de7240","entry":"mish","repo":"digantamisra98/Mish","repo_kind":"official","path":"Mish/Torch/functional.py","file_url":"https://github.com/digantamisra98/Mish/blob/HEAD/Mish/Torch/functional.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e8af53cde1de7240"}},{"code_sha256_prefix":"5e2ed23acb71ee11","entry":"noop","repo":"lessw2020/mish","repo_kind":"listed","path":"mxresnet.py","file_url":"https://github.com/lessw2020/mish/blob/HEAD/mxresnet.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5e2ed23acb71ee11"}},{"code_sha256_prefix":"f0c9a29156911331","entry":"accuracy","repo":"digantamisra98/Mish","repo_kind":"official","path":"exps/train_cifar.py","file_url":"https://github.com/digantamisra98/Mish/blob/HEAD/exps/train_cifar.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f0c9a29156911331"}},{"code_sha256_prefix":"09134815082c4723","entry":"build_model","repo":"digantamisra98/Mish","repo_kind":"official","path":"exps/op_landscape.py","file_url":"https://github.com/digantamisra98/Mish/blob/HEAD/exps/op_landscape.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"09134815082c4723"}},{"code_sha256_prefix":"90dcca0cc0384d13","entry":"convert_to_PIL","repo":"digantamisra98/Mish","repo_kind":"official","path":"exps/op_landscape.py","file_url":"https://github.com/digantamisra98/Mish/blob/HEAD/exps/op_landscape.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"90dcca0cc0384d13"}},{"code_sha256_prefix":"77350704c0889a70","entry":"mish","repo":"digantamisra98/Mish","repo_kind":"official","path":"Mish/TFKeras/mish.py","file_url":"https://github.com/digantamisra98/Mish/blob/HEAD/Mish/TFKeras/mish.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"77350704c0889a70"}},{"code_sha256_prefix":"fe525ef6a5d1473a","entry":"resnet20","repo":"digantamisra98/Mish","repo_kind":"official","path":"exps/resnet.py","file_url":"https://github.com/digantamisra98/Mish/blob/HEAD/exps/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fe525ef6a5d1473a"}},{"code_sha256_prefix":"278ef88735703a97","entry":"resnet32","repo":"digantamisra98/Mish","repo_kind":"official","path":"exps/resnet.py","file_url":"https://github.com/digantamisra98/Mish/blob/HEAD/exps/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"278ef88735703a97"}},{"code_sha256_prefix":"6d73f5ab551aef6b","entry":"resnet44","repo":"digantamisra98/Mish","repo_kind":"official","path":"exps/resnet.py","file_url":"https://github.com/digantamisra98/Mish/blob/HEAD/exps/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6d73f5ab551aef6b"}},{"code_sha256_prefix":"2c3ebef98e7b5f52","entry":"validate","repo":"digantamisra98/Mish","repo_kind":"official","path":"exps/train_cifar.py","file_url":"https://github.com/digantamisra98/Mish/blob/HEAD/exps/train_cifar.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2c3ebef98e7b5f52"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}