Papers › ResNeSt: Split-Attention Networks

ResNeSt: Split-Attention Networks

19 Apr 2020arXiv:2004.08955archive 2025-07-28

Hang Zhang, Chongruo wu, Zhongyue Zhang, Yi Zhu, Haibin Lin, Zhi Zhang, Yue Sun, Tong He, Jonas Mueller, R. Manmatha, Mu Li, Alexander Smola

It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to leverage their success in capturing cross-feature interactions and learning diverse representations. Our design results in a simple and unified computation block, which can be parameterized using only a few variables. Our model, named ResNeSt, outperforms EfficientNet in accuracy and latency trade-off on image classification. In addition, ResNeSt has achieved superior transfer learning results on several public benchmarks serving as the backbone, and has been adopted by the winning entries of COCO-LVIS challenge. The source code for complete system and pretrained models are publicly available.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 48 code samples: 47 from 9 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 48: 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 20 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 41 samples from 8 repositories, 23 ran (16 with no instrument failure; 7 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 9 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 28 samples that ran have no recorded date.

36 repositories listed; official and paper-mentioned ones first.

zhanghang1989/ResNeSt officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
AnudeepKonda/MIMII_anamoly_detection mentioned on GitHubpytorchSyntology: not harvested report
Burf/ResNeSt-Tensorflow2 mentioned on GitHubtfMITSyntology: 8 samples, 4 ran (0 instrument-failed) · 4 unverified report
ChengWeiGu/ResNeSt-Pytorch mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
He-jerry/DSSNet mentioned on GitHubpytorchSyntology: not harvested report
RobertHong1992/Resnest mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
STomoya/ResNeSt mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
YeongHyeon/ResNeSt-TF2 mentioned on GitHubtfMITSyntology: not harvested report
Yuxiang1995/ICDAR2021_MFD mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense... (arXiv:2006.04388; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
ZJCV/ZCls mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RepVGG: Making VGG-style ConvNets Great Again (arXiv:2101.03697; that paper's own run record: 13 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
chongruo/detectron2-resnest mentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 9 ran (5 instrument-failed) · 3 unverified report
ferna11i/detectron2_ResNeST mentioned on GitHubpytorchApache-2.0Syntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
mohitktanwr/Deep-Stem-ResNeSt-ISPRS mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 0 ran · 1 unverified report
mohitktanwr/ResNeSt_Inverse mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
osmr/imgclsmob mentioned on GitHubmxnetMITSyntology: 7 samples, 4 ran (0 instrument-failed) · 3 unverified report
rwightman/pytorch-image-models mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (arXiv:2006.08217; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
sailfish009/detectron2-ResNeSt mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
shellhue/detectron2-ResNeSt mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
thepooons/melanoma-comp-2020 mentioned on GitHubpytorchSyntology: not harvested report
zhanghang1989/PyTorch-Encoding mentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 unverified report
zhanghang1989/detectron2-ResNeSt mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
2023-MindSpore-1/ms-code-216 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code14 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code6 Syntology: not harvested report
Asthestarsfalll/ResNeSt-MegEngine pytorchSyntology: not harvested report
Burf/tfdetection tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified), Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (arXiv:1802.02611; that paper's own run record: 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
MS-Mind/MS-Code-02 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications (arXiv:2206.10589; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
Mind23-2/MindCode-115 mindsporeSyntology: not harvested report
MindSpore-paper-code-2/code2 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: not harvested report
dmlc/gluon-cv tfApache-2.0Syntology: not harvested report
leondgarse/keras_cv_attention_models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RepViT: Revisiting Mobile CNN From ViT Perspective (arXiv:2307.09283; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
open-mmlab/mmdetection pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Open and Comprehensive Pipeline for Unified Object Grounding and Detection (arXiv:2401.02361; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
open-mmlab/mmpose pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation (arXiv:2312.07526; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
gitlab.com/birder/birder pytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

48 samples harvested: 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 20 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran · our draft was wrong
1ran; the contract check could not run
21ran
20unverified

Licence: 23 of the 48 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 9 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

zhanghang1989/ResNeSt official repository 6 samples, 5 ran (0 instrument-failed) · 1 unverified
check_sha1 resnest/utils.py ran Apache-2.0 (permissive) · 3ee0c4bb32b3b945 · report fixture: signature filename:str/0/str, sha1_hash:str/0/str · returned bool · level recorded 2026-09-25
get_model_file in 15 papers resnest/gluon/model_store.py ran Apache-2.0 (permissive) · 1ef6246b268a5705 · report fixture: returned str · level recorded 2026-09-25
make_stage resnest/d2/resnest.py ran Apache-2.0 (permissive) · 7e206a38c0ece70d · report fixture: signature block_class:callable/0/?, num_blocks:int/0/int, first_stride:int/0/int, in_channels:int/0/int, out_channels:int/0/int · returned list · level recorded 2026-09-25
short_hash in 15 papers resnest/gluon/model_store.py ran Apache-2.0 (permissive) · b06092cd4eb27a10 · report fixture: signature name:str/0/str · returned str · level recorded 2026-09-25
unzip in 8 papers resnest/utils.py ran Apache-2.0 (permissive) · 79a96a9c7fd65ce5 · report fixture: signature zip_file_path:str/0/str, root:str/0/str · returned str · level recorded 2026-09-25
download in 53 papers resnest/utils.py unverified Apache-2.0 (permissive) · eb12eb65d87b258c · report
Burf/ResNeSt-Tensorflow2 community (archive-listed) 8 samples, 4 ran (0 instrument-failed) · 4 unverified
group_conv resnest/splat.py ran MIT (permissive) · 21a473c9ae1aa4ca · report fixture: signature x:EagerTensor/4/float, filters:int/0/int, kernel_size:list/1/int, padding:str/0/str, activation:str/0/str, name:str/0/str · returned EagerTensor · level recorded 2026-09-24
load_weight resnest/resnest.py ran MIT (permissive) · aea5d02e03df9b82 · report fixture: signature keras_model:callable/0/?, torch_url:str/0/str, group_size:int/0/int · returned MinimalKerasModel · level recorded 2026-09-24
resnest50 resnest/resnest.py ran MIT (permissive) · b55f89f2f2fe736d · report fixture: returned Functional · level recorded 2026-09-24
split_attention_block resnest/splat.py ran MIT (permissive) · 8fc30ed2b4a12eb8 · report fixture: signature x:EagerTensor/4/float, n_filter:int/0/int, kernel_size:int/0/int, stride_size:int/0/int, dilation:int/0/int, group_size:int/0/int, radix:int/0/int, dropout_rate:float/0/float, expansion:int/0/int, prefix:str/0/str · returned EagerTensor · level recorded 2026-09-24
ResNet in 139 papers resnest/resnet.py unverified MIT (permissive) · 8209cb3497010910 · report
resnest_block resnest/resnet.py unverified MIT (permissive) · 2196103dc7afecbd · report
resnest_module resnest/resnet.py unverified MIT (permissive) · 4d6569a50c288057 · report
rsoftmax resnest/splat.py unverified MIT (permissive) · afc4cda18f695c8a · report
ChengWeiGu/ResNeSt-Pytorch community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
load_pkl_data train_resneSt.py ran · our draft was wrong no licence file found · pointer only · 116a44af0a09b23d · report fixture: signature dataset_dst:str/0/str · returned dict · level recorded, date not recorded
change_output_layers train_resneSt.py unverified no licence file found · pointer only · b74fa21880286e7a · report
RobertHong1992/Resnest community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
short_hash in 15 papers core/resnest.py ran · our draft was wrong no licence file found · pointer only · 979123ace229d553 · report fixture: signature name:str/0/str · returned str · level recorded, date not recorded
resnest101 core/resnest.py unverified no licence file found · pointer only · ab6e7a32f07c96d1 · report
resnest50 core/resnest.py unverified no licence file found · pointer only · d78c4213925c9d95 · report
chongruo/detectron2-resnest community (archive-listed) 12 samples, 9 ran (5 instrument-failed) · 3 unverified
batched_nms in 29 papers detectron2/layers/nms.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 0df9d3b583fbc6cb · report fixture: signature boxes:Tensor/2/float, scores:Tensor/1/float, idxs:Tensor/1/int, iou_threshold:float/0/float · returned Tensor · level recorded 2026-09-24
cat in 32 papers detectron2/layers/wrappers.py ran; the contract check could not run (RAISES) Apache-2.0 recorded; this copy not marked cleared · pointer only · 6cbf46794989b731 · report fixture: signature tensors:list/1/Tensor, dim:int/0/int · returned Tensor · level recorded 2026-09-22
convert_basic_c2_names in 46 papers detectron2/checkpoint/c2_model_loading.py ran · our draft was wrong Apache-2.0 recorded; this copy not marked cleared · pointer only · e8526a516b4f9206 · report fixture: signature original_keys:list/1/str · returned list · level recorded 2026-09-24
convert_c2_detectron_names in 45 papers detectron2/checkpoint/c2_model_loading.py ran · our draft was wrong Apache-2.0 recorded; this copy not marked cleared · pointer only · 52810b504f0d1066 · report fixture: signature weights:dict/0/? · returned tuple · level recorded 2026-09-24
get_checkpoint_url in 7 papers detectron2/model_zoo/model_zoo.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 22f71a6d1391bbe3 · report fixture: signature config_path:str/0/str · returned str · level recorded 2026-09-25
interpolate in 95 papers detectron2/layers/wrappers.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · e3055ddd5ac36b0b · report fixture: signature input:Tensor/4/float, size:tuple/1/int, scale_factor:NoneType/0/?, mode:str/0/str, align_corners:NoneType/0/? · returned Tensor · level recorded 2026-09-25
pad_masks in 23 papers detectron2/layers/mask_ops.py ran · our draft was wrong fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 406f84cf799ed34d · report fixture: signature masks:Tensor/3/float, padding:int/0/int · returned tuple · level recorded 2026-09-24
paste_mask_in_image_old in 23 papers detectron2/layers/mask_ops.py ran · our draft was wrong Apache-2.0 recorded; this copy not marked cleared · pointer only · d03592674030077f · report fixture: signature mask:Tensor/2/float, box:Tensor/1/float, img_h:int/0/int, img_w:int/0/int, threshold:float/0/float · returned Tensor · level recorded 2026-09-24
paste_masks_in_image in 20 papers detectron2/layers/mask_ops.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 13b3f33534eea02a · report fixture: signature masks:Tensor/3/float, boxes:Tensor/2/float, image_shape:tuple/1/int, threshold:float/0/float · returned Tensor · level recorded 2026-09-25
batched_nms_rotated in 22 papers detectron2/layers/nms.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 4845964b76bba6c5 · report
get_config_file in 13 papers detectron2/model_zoo/model_zoo.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 10d4b4b249a78f42 · report
nms_rotated in 22 papers detectron2/layers/nms.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · d3fa37a000ad294d · report
ferna11i/detectron2_ResNeST community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
batched_nms in 29 papers detectron2/layers/nms.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · a608182a325f07f7 · report fixture: signature boxes:Tensor/2/float, scores:Tensor/1/float, idxs:Tensor/1/int, iou_threshold:float/0/float · returned Tensor · level recorded 2026-09-24
cat in 32 papers detectron2/layers/wrappers.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 7664e656f28eeecc · report fixture: signature tensors:list/1/Tensor, dim:int/0/int · returned Tensor · level recorded 2026-09-24
nonzero_tuple detectron2/layers/wrappers.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · eb03e701fa2c3245 · report fixture: signature x:Tensor/2/float · returned tuple · level recorded 2026-09-24
paste_masks_in_image in 20 papers detectron2/layers/mask_ops.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 5837267fa2aed31c · report fixture: signature masks:Tensor/3/float, boxes:Tensor/2/float, image_shape:tuple/1/int, threshold:float/0/float · returned Tensor · level recorded 2026-09-25
batched_nms_rotated in 22 papers detectron2/layers/nms.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 65735d51d64903a4 · report
mohitktanwr/Deep-Stem-ResNeSt-ISPRS community (archive-listed) 1 sample, 0 ran · 1 unverified
get_model_file in 15 papers resnest/gluon/model_store.py unverified Apache-2.0 (permissive) · 2cd24f5ed4aae254 · report
osmr/imgclsmob community (archive-listed) 7 samples, 4 ran (0 instrument-failed) · 3 unverified
calc_block_num_params gluon/model_stats.py ran MIT (permissive) · 1e94f0e5aae421b2 · report fixture: signature block:Block/0/? · returned int64 · level recorded 2026-09-24
calc_sha1 prep_model.py ran MIT (permissive) · 413e0014f62a9efc · report fixture: signature file_name:str/0/str · returned str · level recorded 2026-09-24
post_process in 56 papers prep_model.py ran MIT (permissive) · 8f535a7e6722bc55 · report fixture: signature dst_dir_path:str/0/str, model_name:str/0/str, model_file_path:str/0/str, log_file_path:str/0/str, dst_model_file_ext:str/0/str, log_line_num:int/0/int · returned tuple · level recorded 2026-09-24
prepare_dst_model convert_models.py ran MIT (permissive) · 16e0587d2f35fcdf · report fixture: signature dst_fwk:str/0/str, dst_model:str/0/str, src_fwk:str/0/str, ctx:NoneType/0/?, use_cuda:bool/0/bool, num_classes:int/0/int, in_channels:int/0/int, model_type:str/0/str · returned tuple · level recorded 2026-09-24
calc_block_num_params2 gluon/model_stats.py unverified MIT (permissive) · 45160e9713d39dfa · report
convert_pt2pt convert_models.py unverified MIT (permissive) · cce15073ab760551 · report
prepare_src_model convert_models.py unverified MIT (permissive) · df0046e7135787f9 · report
zhanghang1989/PyTorch-Encoding community (archive-listed) 3 samples, 0 ran · 3 unverified
resnest101 encoding/models/backbone/resnest.py unverified MIT (permissive) · 7b2de4494236346e · report
resnest200 encoding/models/backbone/resnest.py unverified MIT (permissive) · e9769d275b2aeaab · report
resnest50 encoding/models/backbone/resnest.py unverified MIT (permissive) · 6b650e26ef7115fd · report
Repository not located 1 sample, 0 ran · 1 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
repository not located unverified licence of this copy not recorded · 913d82af53065418 · report

Tasks

Image ClassificationInstance SegmentationObject DetectionPanoptic SegmentationSemantic SegmentationTransfer Learningimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet ResNeSt-269 Number of params 111M #313 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeSt-269 Top 1 Accuracy 84.5% #313 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeSt-200 Number of params 70M #381 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeSt-200 Top 1 Accuracy 83.9% #381 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeSt-101 Number of params 48M #480 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeSt-101 Top 1 Accuracy 83.0% #480 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeSt-50 GFLOPs 5.39 #658 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeSt-50 Number of params 27.5M #658 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeSt-50 Top 1 Accuracy 81.13% #658 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeSt-50-fast GFLOPs 4.34 #689 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeSt-50-fast Number of params 27.5M #689 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeSt-50-fast Top 1 Accuracy 80.64% #689 of 1060 Archive leaderboard report
Instance Segmentation COCO minival ResNeSt-200 (multi-scale) mask AP 46.25 #43 of 93 Archive leaderboard report
Instance Segmentation COCO minival ResNeSt-200-DCN (single-scale) mask AP 44.5 #53 of 93 Archive leaderboard report
Instance Segmentation COCO minival ResNeSt-200 (single-scale) mask AP 44.21 #57 of 93 Archive leaderboard report
Instance Segmentation COCO minival ResNeSt-101 (single-scale) mask AP 41.56 #65 of 93 Archive leaderboard report
Instance Segmentation COCO test-dev ResNeSt101 mask AP 43% #51 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev ResNeSt-200 (multi-scale) AP50 70.2 #108 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev ResNeSt-200 (multi-scale) AP75 51.5 #108 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev ResNeSt-200 (multi-scale) APL 60.6 #108 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev ResNeSt-200 (multi-scale) APM 49.6 #108 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev ResNeSt-200 (multi-scale) APS 30.0 #108 of 112 Archive leaderboard report
Object Detection COCO minival ResNeSt-200 (multi-scale) AP50 71.00 #65 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200 (multi-scale) AP75 57.07 #65 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200 (multi-scale) APL 66.29 #65 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200 (multi-scale) APM 56.36 #65 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200 (multi-scale) APS 36.80 #65 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200 (multi-scale) box AP 52.47 #65 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200-DCN (single-scale) AP50 69.53 #75 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200-DCN (single-scale) AP75 55.40 #75 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200-DCN (single-scale) APL 65.83 #75 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200-DCN (single-scale) APM 54.66 #75 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200-DCN (single-scale) APS 32.67 #75 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200-DCN (single-scale) box AP 50.91 #75 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200 (single-scale) AP50 68.78 #77 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200 (single-scale) AP75 55.17 #77 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200 (single-scale) APL 63.9 #77 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200 (single-scale) APM 54.2 #77 of 220 Archive leaderboard report
Object Detection COCO minival ResNeSt-200 (single-scale) box AP 50.54 #77 of 220 Archive leaderboard report
Object Detection COCO test-dev ResNeSt-200 (multi-scale) AP50 72.0 #63 of 225 Archive leaderboard report
Object Detection COCO test-dev ResNeSt-200 (multi-scale) AP75 58.0 #63 of 225 Archive leaderboard report
Object Detection COCO test-dev ResNeSt-200 (multi-scale) APL 66.8 #63 of 225 Archive leaderboard report
Object Detection COCO test-dev ResNeSt-200 (multi-scale) APM 56.2 #63 of 225 Archive leaderboard report
Object Detection COCO test-dev ResNeSt-200 (multi-scale) APS 35.1 #63 of 225 Archive leaderboard report
Object Detection COCO test-dev ResNeSt-200 (multi-scale) box mAP 53.3 #63 of 225 Archive leaderboard report
Panoptic Segmentation COCO minival PanopticFPN+ResNeSt(single-scale) PQ 47.9 #24 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival PanopticFPN+ResNeSt(single-scale) PQst 37.0 #24 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival PanopticFPN+ResNeSt(single-scale) PQth 55.1 #24 of 31 Archive leaderboard report
Semantic Segmentation ADE20K ResNeSt-200 Validation mIoU 48.36 #147 of 235 Archive leaderboard report
Semantic Segmentation ADE20K ResNeSt-269 Validation mIoU 47.60 #160 of 235 Archive leaderboard report
Semantic Segmentation ADE20K ResNeSt-101 Validation mIoU 46.91 #168 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val ResNeSt-200 mIoU 48.36 #62 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val ResNeSt-269 mIoU 47.60 #65 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val ResNeSt-101 mIoU 46.91 #68 of 95 Archive leaderboard report
Semantic Segmentation Cityscapes test ResNeSt200 (Mapillary) Mean IoU (class) 83.3% #16 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes val ResNeSt-200 mIoU 82.7 #32 of 99 Archive leaderboard report
Semantic Segmentation DADA-seg ResNeSt (ResNeSt-101) mIoU 19.99 #21 of 28 Archive leaderboard report
Semantic Segmentation PASCAL Context ResNeSt-269 mIoU 58.9 #17 of 66 Archive leaderboard report
Semantic Segmentation PASCAL Context ResNeSt-200 mIoU 58.4 #19 of 66 Archive leaderboard report
Semantic Segmentation PASCAL Context ResNeSt-101 mIoU 56.5 #23 of 66 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: ResNeSt

1x1 ConvolutionASPPAutoAugmentAverage PoolingBatch NormalizationColorJitterConvolutionCosine AnnealingCutoutDeepLabv3Deformable ConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDilated ConvolutionDropBlockDropoutEfficientNetFPNGlobal Average PoolingImage Scale AugmentationInverted Residual BlockKaiming InitializationLSTMLabel SmoothingLinear Warmup With Cosine AnnealingMixupPointwise ConvolutionRMSPropRandom Horizontal FlipRandom Resized CropReLUResNeStResidual ConnectionRoIAlignSGD with MomentumSigmoid ActivationSoftmaxSpatial Pyramid PoolingSplit AttentionSqueeze-and-Excitation BlockTanh ActivationWeight Decay

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