Papers › SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks

SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks

31 Dec 2018CVPR 2019 6arXiv:1812.11703archive 2025-07-28

Bo Li, Wei Wu, Qiang Wang, Fangyi Zhang, Junliang Xing, Junjie Yan

Siamese network based trackers formulate tracking as convolutional feature cross-correlation between target template and searching region. However, Siamese trackers still have accuracy gap compared with state-of-the-art algorithms and they cannot take advantage of feature from deep networks, such as ResNet-50 or deeper. In this work we prove the core reason comes from the lack of strict translation invariance. By comprehensive theoretical analysis and experimental validations, we break this restriction through a simple yet effective spatial aware sampling strategy and successfully train a ResNet-driven Siamese tracker with significant performance gain. Moreover, we propose a new model architecture to perform depth-wise and layer-wise aggregations, which not only further improves the accuracy but also reduces the model size. We conduct extensive ablation studies to demonstrate the effectiveness of the proposed tracker, which obtains currently the best results on four large tracking benchmarks, including OTB2015, VOT2018, UAV123, and LaSOT. Our model will be released to facilitate further studies based on this problem.

PaperPDFConference PDFCodeCode 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 17 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 17 samples from 2 repositories, 12 ran (9 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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.

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

STVIR/pysot mentioned on GitHubpytorchApache-2.0Syntology: 7 samples, 5 ran (2 instrument-failed) · 2 unverified report
logiklesuraj/SiamFC mentioned on GitHubpytorchSyntology: not harvested report
logiklesuraj/siamfcex mentioned on GitHubpytorchSyntology: not harvested report
lql-team/TSDM mentioned on GitHubpytorchSyntology: not harvested report
pengboxiangshang/siamrpn mentioned on GitHubpytorchSyntology: not harvested report
shallowtoil/DROL mentioned on GitHubpytorchApache-2.0Syntology: 10 samples, 7 ran (1 instrument-failed) · 3 unverified report
xingpingdong/CLNet-tracking mentioned on GitHubpytorchSyntology: not harvested report
zllrunning/SiameseX.PyTorch mentioned on GitHubpytorchSyntology: not harvested report
2023-MindSpore-1/ms-code-216 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code11 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code14 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code14 mindsporeSyntology: not harvested report
open-mmlab/mmtracking pytorchApache-2.0Syntology: 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.

Code Syntology ran Syntology

17 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
9ran
5unverified

Licence: 2 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

STVIR/pysot community (archive-listed) 7 samples, 5 ran (2 instrument-failed) · 2 unverified
conv3x3 in 1,376 papers pysot/models/backbone/resnet_atrous.py ran · our draft was wrong Apache-2.0 (permissive) · 48468b2c75aae583 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, dilation:int/0/int · returned Conv2d · level recorded 2026-09-24
conv_1x1_bn in 59 papers pysot/models/backbone/mobile_v2.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · a0131fb70c267a9e · report fixture: signature inp:int/0/int, oup:int/0/int · returned Sequential · level recorded 2026-09-22
conv_bn in 88 papers pysot/models/backbone/mobile_v2.py ran Apache-2.0 (permissive) · c46a07169e517d67 · report fixture: signature inp:int/0/int, oup:int/0/int, stride:int/0/int, padding:int/0/int · returned Sequential · level recorded 2026-09-25
get_cls_loss in 7 papers pysot/models/loss.py ran Apache-2.0 (permissive) · c15bf5953bf452e6 · report fixture: signature pred:Tensor/2/float, label:Tensor/1/int, select:Tensor/1/int · returned Tensor · level recorded 2026-09-25
select_cross_entropy_loss in 6 papers pysot/models/loss.py ran Apache-2.0 (permissive) · 608039b454e6bd80 · report fixture: signature pred:Tensor/2/float, label:Tensor/1/int · returned float · level recorded 2026-09-25
load_pretrain in 11 papers pysot/utils/model_load.py unverified Apache-2.0 (permissive) · 1023e0f5057a4383 · report
xcorr_slow in 5 papers pysot/core/xcorr.py unverified Apache-2.0 (permissive) · 74d343344c065353 · report
shallowtoil/DROL community (archive-listed) 10 samples, 7 ran (1 instrument-failed) · 3 unverified
check_keys in 10 papers pysot/utils/model_load.py ran Apache-2.0 (permissive) · ec73a18eb6cee64f · report fixture: signature model:callable/0/?, pretrained_state_dict:dict/0/? · returned bool · level recorded 2026-09-25
get_cls_loss in 7 papers pysot/models/loss.py ran Apache-2.0 (permissive) · 3f1957b700e9ed16 · report fixture: signature pred:Tensor/2/float, label:Tensor/1/int, select:Tensor/1/int · returned Tensor · level recorded 2026-09-25
remove_prefix in 26 papers pysot/utils/model_load.py ran Apache-2.0 (permissive) · a57313630ecbb3a1 · report fixture: signature state_dict:dict/0/?, prefix:str/0/str · returned dict · level recorded 2026-09-25
select_cross_entropy_loss in 6 papers pysot/models/loss.py ran Apache-2.0 (permissive) · dd9b577439973333 · report fixture: signature pred:Tensor/2/float, label:Tensor/1/int · returned float · level recorded 2026-09-25
weight_l1_loss pysot/models/loss.py ran Apache-2.0 (permissive) · 1e0c0beeea78d234 · report fixture: signature pred_loc:Tensor/4/float, label_loc:Tensor/5/float, loss_weight:Tensor/4/float · returned Tensor · level recorded 2026-09-25
xcorr_depthwise in 9 papers pysot/core/xcorr.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 541e18bc31d27b44 · report fixture: signature x:Tensor/4/float, kernel:Tensor/4/float · returned Tensor · level recorded 2026-09-22
xcorr_fast in 5 papers pysot/core/xcorr.py ran fingerprinted Apache-2.0 (permissive) · 928a6daecaca5912 · report fixture: signature x:Tensor/4/float, kernel:Tensor/4/float · returned Tensor · level recorded 2026-09-25
convert in 76 papers experiments/siamfc_alex_upxcorr_otb/convert_model.py unverified Apache-2.0 (permissive) · c5f1762f86318309 · report
load_pretrain in 11 papers pysot/utils/model_load.py unverified Apache-2.0 (permissive) · 767a6a8efacc5da5 · report
xcorr_slow in 5 papers pysot/core/xcorr.py unverified Apache-2.0 (permissive) · 9e0c207732f3e7a5 · report

Tasks

TranslationVisual Object TrackingVisual Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Object Tracking TrackingNet SiamRPN++ Accuracy 70 #34 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet SiamRPN++ Normalized Precision 79.98 #34 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet SiamRPN++ Precision 69.38 #34 of 40 Archive leaderboard report
Visual Object Tracking VOT2017/18 SiamRPN++ Expected Average Overlap (EAO) 0.414 #5 of 15 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.

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