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 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="1812.11703")

Code

Syntology Ran 3 of 17 code samples harvested from 2 repositories linked to this paper; 14 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 1 ran with no contract checked.

By repository: community (archive-listed): 17 samples from 2 repositories, 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.

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

STVIR/pysot mentioned on GitHubpytorchApache-2.0 report
logiklesuraj/SiamFC mentioned on GitHubpytorch report
logiklesuraj/siamfcex mentioned on GitHubpytorch report
lql-team/TSDM mentioned on GitHubpytorch report
pengboxiangshang/siamrpn mentioned on GitHubpytorch report
shallowtoil/DROL mentioned on GitHubpytorchApache-2.0 report
xingpingdong/CLNet-tracking mentioned on GitHubpytorch report
zllrunning/SiameseX.PyTorch mentioned on GitHubpytorch report
open-mmlab/mmtracking pytorchApache-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

17 samples harvested; 3 ran; 0 honoured the contract we drafted; 14 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.

2ran · our draft was wrong
1ran
14unverified

Licence: 0 of the 17 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.

conv3x3 STVIR/pysot/pysot/models/backbone/resnet_atrous.py community (archive-listed) ran Apache-2.0 (permissive) · 48468b2c75aae583 · report
conv_1x1_bn STVIR/pysot/pysot/models/backbone/mobile_v2.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · a0131fb70c267a9e · report
xcorr_depthwise shallowtoil/DROL/pysot/core/xcorr.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 541e18bc31d27b44 · report
check_keys shallowtoil/DROL/pysot/utils/model_load.py community (archive-listed) unverified Apache-2.0 (permissive) · ec73a18eb6cee64f · report
conv_bn STVIR/pysot/pysot/models/backbone/mobile_v2.py community (archive-listed) unverified Apache-2.0 (permissive) · c46a07169e517d67 · report
convert shallowtoil/DROL/experiments/siamfc_alex_upxcorr_otb/convert_model.py community (archive-listed) unverified Apache-2.0 (permissive) · c5f1762f86318309 · report
get_cls_loss STVIR/pysot/pysot/models/loss.py community (archive-listed) unverified Apache-2.0 (permissive) · c15bf5953bf452e6 · report
get_cls_loss shallowtoil/DROL/pysot/models/loss.py community (archive-listed) unverified Apache-2.0 (permissive) · 3f1957b700e9ed16 · report
load_pretrain STVIR/pysot/pysot/utils/model_load.py community (archive-listed) unverified Apache-2.0 (permissive) · 1023e0f5057a4383 · report
load_pretrain shallowtoil/DROL/pysot/utils/model_load.py community (archive-listed) unverified Apache-2.0 (permissive) · 767a6a8efacc5da5 · report
remove_prefix shallowtoil/DROL/pysot/utils/model_load.py community (archive-listed) unverified Apache-2.0 (permissive) · a57313630ecbb3a1 · report
select_cross_entropy_loss STVIR/pysot/pysot/models/loss.py community (archive-listed) unverified Apache-2.0 (permissive) · 608039b454e6bd80 · report
select_cross_entropy_loss shallowtoil/DROL/pysot/models/loss.py community (archive-listed) unverified Apache-2.0 (permissive) · dd9b577439973333 · report
weight_l1_loss shallowtoil/DROL/pysot/models/loss.py community (archive-listed) unverified Apache-2.0 (permissive) · 1e0c0beeea78d234 · report
xcorr_fast shallowtoil/DROL/pysot/core/xcorr.py community (archive-listed) unverified Apache-2.0 (permissive) · 928a6daecaca5912 · report
xcorr_slow STVIR/pysot/pysot/core/xcorr.py community (archive-listed) unverified Apache-2.0 (permissive) · 74d343344c065353 · report
xcorr_slow shallowtoil/DROL/pysot/core/xcorr.py community (archive-listed) 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