Papers › Scale Equivariance Improves Siamese Tracking

Scale Equivariance Improves Siamese Tracking

17 Jul 2020arXiv:2007.09115archive 2025-07-28

Ivan Sosnovik, Artem Moskalev, Arnold Smeulders

Siamese trackers turn tracking into similarity estimation between a template and the candidate regions in the frame. Mathematically, one of the key ingredients of success of the similarity function is translation equivariance. Non-translation-equivariant architectures induce a positional bias during training, so the location of the target will be hard to recover from the feature space. In real life scenarios, objects undergoe various transformations other than translation, such as rotation or scaling. Unless the model has an internal mechanism to handle them, the similarity may degrade. In this paper, we focus on scaling and we aim to equip the Siamese network with additional built-in scale equivariance to capture the natural variations of the target a priori. We develop the theory for scale-equivariant Siamese trackers, and provide a simple recipe for how to make a wide range of existing trackers scale-equivariant. We present SE-SiamFC, a scale-equivariant variant of SiamFC built according to the recipe. We conduct experiments on OTB and VOT benchmarks and on the synthetically generated T-MNIST and S-MNIST datasets. We demonstrate that a built-in additional scale equivariance is useful for visual object tracking.

PaperPDFCodeCode 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="2007.09115")

Code

Syntology Ran 1 of 12 code samples harvested from 1 repository linked to this paper; 11 have no recorded run. Of those that ran: 1 ran · honoured contract.

By repository: official repository: 12 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

isosnovik/SiamSE officialmentioned in papermentioned on GitHubpytorchMIT 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; 1 ran; 1 honoured the contract we drafted; 11 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.

1ran · honoured contract
11unverified

Licence: 11 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 isosnovik/SiamSE. “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.

to_torch isosnovik/SiamSE/lib/utils.py official repository ran · honoured contract MIT (permissive) · 516e33dfd5c4f7df · report
compute_success_error isosnovik/SiamSE/lib/core/eval_otb.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · f86208e35c785fc3 · report
compute_success_overlap isosnovik/SiamSE/lib/core/eval_otb.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · f3d656c62034650e · report
convert_color_RGB isosnovik/SiamSE/lib/utils.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · 6dc1cecb20fe886b · report
convert_param_name_to_layer isosnovik/SiamSE/transfer_weights.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · 887a60be88c150f4 · report
eval_eao isosnovik/SiamSE/lib/core/eval_vot.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · a1c6d988947dcd54 · report
im_to_torch isosnovik/SiamSE/lib/utils.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · 9d479ebc22256e35 · report
is_valid_number isosnovik/SiamSE/lib/core/function.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · 253107dc24b4b2c4 · report
overlap_ratio isosnovik/SiamSE/lib/core/eval_otb.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · a99c8e460592f3b5 · report
siamfc_train isosnovik/SiamSE/lib/core/function.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · 28860c4d8893f14b · report
tikhonov_reg_lstsq isosnovik/SiamSE/transfer_weights.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · 988c82eedbfc1f51 · report
unfix_more isosnovik/SiamSE/lib/core/function.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · 94f66257d3e415fe · report

Tasks

Object TrackingTranslationVisual Object TrackingVisual Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Object Tracking OTB-2013 SE-SiamFC AUC 0.68 #1 of 7 Archive leaderboard report
Visual Object Tracking OTB-2015 SE-SiamFC AUC 0.66 #13 of 18 Archive leaderboard report
Visual Object Tracking VOT2016 SE-SiamFC Expected Average Overlap (EAO) 0.36 #4 of 6 Archive leaderboard report
Visual Object Tracking VOT2017 SE-SiamFC Expected Average Overlap (EAO) 0.27 #4 of 6 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

Siamese Network

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