SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.09115 · 2020

Scale Equivariance Improves Siamese Tracking

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 1 failure of our instrument; 3 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2007.09115.json · badge: /api/ran/2007.09115.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
isosnovik/SiamSE canonical (classifier label)
classifier basis: census
9 ran · 3 no recorded run
FunctionStatusWhere it lives
compute_success_error Ran
ran on a synthesized input
isosnovik/SiamSE/lib/core/eval_otb.py
pointer only (licence: MIT) · get_code("f86208e35c785fc3")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, isosnovik/SiamSE, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_success_overlap Ran
ran on a synthesized input
isosnovik/SiamSE/lib/core/eval_otb.py
pointer only (licence: MIT) · get_code("f3d656c62034650e")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, isosnovik/SiamSE, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_color_RGB Ran
ran on a synthesized input
isosnovik/SiamSE/lib/utils.py
pointer only (licence: MIT) · get_code("6dc1cecb20fe886b")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, isosnovik/SiamSE, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_param_name_to_layer Ran
ran on a synthesized input
isosnovik/SiamSE/transfer_weights.py
pointer only (licence: MIT) · get_code("887a60be88c150f4")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, isosnovik/SiamSE, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

im_to_torch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
isosnovik/SiamSE/lib/utils.py
pointer only (licence: MIT) · get_code("9d479ebc22256e35")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, isosnovik/SiamSE, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

is_valid_number Ran
ran on a synthesized input
isosnovik/SiamSE/lib/core/function.py
pointer only (licence: MIT) · get_code("253107dc24b4b2c4")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, isosnovik/SiamSE, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

overlap_ratio Ran
ran on a synthesized input
isosnovik/SiamSE/lib/core/eval_otb.py
pointer only (licence: MIT) · get_code("a99c8e460592f3b5")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, isosnovik/SiamSE, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

tikhonov_reg_lstsq Ran
ran on a synthesized input
isosnovik/SiamSE/transfer_weights.py
pointer only (licence: MIT) · get_code("988c82eedbfc1f51")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, isosnovik/SiamSE, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

to_torch Ran
ran, honoured the contract we drafted
isosnovik/SiamSE/lib/utils.py
code served (permissive licence) · get_code("516e33dfd5c4f7df")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# to_torch takes an ndarray and converts it to a torch tensor
# It only calls torch.from_numpy on the input
ndarray = np.array([[1.0, 2.0, 3.0, 4.0],
                     [5.0, 6.0, 7.0, 8.0]], dtype=np.float32)

ARGS = {
    "ndarray": ndarray
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
eval_eao Not yet run
unverified (harvested, no recorded run)
isosnovik/SiamSE/lib/core/eval_vot.py
pointer only (licence: MIT) · get_code("a1c6d988947dcd54")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, isosnovik/SiamSE, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

siamfc_train Not yet run
unverified (harvested, no recorded run)
isosnovik/SiamSE/lib/core/function.py
pointer only (licence: MIT) · get_code("28860c4d8893f14b")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, isosnovik/SiamSE, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

unfix_more Not yet run
unverified (harvested, no recorded run)
isosnovik/SiamSE/lib/core/function.py
pointer only (licence: MIT) · get_code("94f66257d3e415fe")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, isosnovik/SiamSE, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
compute_success_error 1 other paper
1 later
2008.02745 (2020-08)
Towards Accurate Pixel-wise Object Tracking by Attention Retrieval
compute_success_overlap 1 other paper
1 later
2008.02745 (2020-08)
Towards Accurate Pixel-wise Object Tracking by Attention Retrieval
im_to_torch 1 other paper
1 later
2104.14545 (2021-04)
LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
overlap_ratio 1 other paper
1 later
2008.02745 (2020-08)
Towards Accurate Pixel-wise Object Tracking by Attention Retrieval
to_torch 1 other paper
1 later
2104.14545 (2021-04)
LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2007.09115")
get_code_for_paper("2007.09115")
have("2007.09115")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2007.09115.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2007.09115.svg)](https://syntology.ai/paper/2007.09115)

Connect an agent — have() is free.