SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.05077 · 2020

SEKD: Self-Evolving Keypoint Detection and Description

arXiv · PDF · Open in the Atlas

Code that ran

5 of 11 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; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 0 failures of our instrument; 6 no recorded run), measured 2026-11-22; 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/2006.05077.json · badge: /api/ran/2006.05077.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
aliyun/Self-Evolving-Keypoint-Demo community (classifier label)
classifier basis not recorded on the link
5 ran · 6 no recorded run
FunctionStatusWhere it lives
binary_focal_loss Ran
ran on a synthesized input
aliyun/Self-Evolving-Keypoint-Demo/loss/loss_focal.py
pointer only (licence: MIT) · get_code("1c50fa2fbc860726")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, aliyun/Self-Evolving-Keypoint-Demo, 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.

calculate_displacement Ran
ran on a synthesized input
aliyun/Self-Evolving-Keypoint-Demo/nets/sekd.py
pointer only (licence: MIT) · get_code("25583f01c7a1051a")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, aliyun/Self-Evolving-Keypoint-Demo, 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.

focal_loss Ran
ran on a synthesized input
aliyun/Self-Evolving-Keypoint-Demo/loss/loss_focal.py
pointer only (licence: MIT) · get_code("deb13554676659ec")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, aliyun/Self-Evolving-Keypoint-Demo, 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.

generate_read_function Ran
ran on a synthesized input
aliyun/Self-Evolving-Keypoint-Demo/evaluate_homography.py
pointer only (licence: MIT) · get_code("6bad5b3acd244193")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, aliyun/Self-Evolving-Keypoint-Demo, 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.

mnn_matcher Ran
ran on a synthesized input
aliyun/Self-Evolving-Keypoint-Demo/evaluate_homography.py
pointer only (licence: MIT) · get_code("a2c6f68f82eb1784")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, aliyun/Self-Evolving-Keypoint-Demo, 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.

benchmark_features Not yet run
unverified (harvested, no recorded run)
aliyun/Self-Evolving-Keypoint-Demo/evaluate_homography.py
pointer only (licence: MIT) · get_code("06834635ea29cb25")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, aliyun/Self-Evolving-Keypoint-Demo, 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.

benchmark_features Not yet run
unverified (harvested, no recorded run)
aliyun/Self-Evolving-Keypoint-Demo/evaluate_mpn.py
pointer only (licence: MIT) · get_code("b4199ed15b0438ca")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, aliyun/Self-Evolving-Keypoint-Demo, 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.

benchmark_features Not yet run
unverified (harvested, no recorded run)
aliyun/Self-Evolving-Keypoint-Demo/evaluate_repeatability.py
pointer only (licence: MIT) · get_code("be223a7a33ac4ba0")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, aliyun/Self-Evolving-Keypoint-Demo, 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.

loss_L2Net Not yet run
unverified (harvested, no recorded run)
aliyun/Self-Evolving-Keypoint-Demo/loss/loss_l2net.py
pointer only (licence: MIT) · get_code("3085901f03841471")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, aliyun/Self-Evolving-Keypoint-Demo, 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.

loss_random_sampling Not yet run
unverified (harvested, no recorded run)
aliyun/Self-Evolving-Keypoint-Demo/loss/loss_random_sampling.py
pointer only (licence: MIT) · get_code("80f6f9d30c73e125")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, aliyun/Self-Evolving-Keypoint-Demo, 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.

one_hot Not yet run
unverified (harvested, no recorded run)
aliyun/Self-Evolving-Keypoint-Demo/loss/loss_focal.py
pointer only (licence: MIT) · get_code("7b7e414e3d968b19")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, aliyun/Self-Evolving-Keypoint-Demo, 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 10 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
loss_random_sampling 1 other paper
1 dated earlier
1908.05547 (2019-08)
Beyond Cartesian Representations for Local Descriptors

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 2026-11-22.

Repositories linked to this paper

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

Abstract

Researchers have attempted utilizing deep neural network (DNN) to learn novel local features from images inspired by its recent successes on a variety of vision tasks. However, existing DNN-based algorithms have not achieved such remarkable progress that could be partly attributed to insufficient utilization of the interactive characters between local feature detector and descriptor. To alleviate these difficulties, we emphasize two desired properties, i.e., repeatability and reliability, to simultaneously summarize the inherent and interactive characters of local feature detector and descriptor. Guided by these properties, a self-supervised framework, namely self-evolving keypoint detection and description (SEKD), is proposed to learn an advanced local feature model from unlabeled natural images. Additionally, to have performance guarantees, novel training strategies have also been dedicatedly designed to minimize the gap between the learned feature and its properties. We benchmark the proposed method on homography estimation, relative pose estimation, and structure-from-motion tasks. Extensive experimental results demonstrate that the proposed method outperforms popular hand-crafted and DNN-based methods by remarkable margins. Ablation studies also verify the effectiveness of each critical training strategy. We will release our code along with the trained model publicly.

For agents

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

get_harvested_code_for_paper("2006.05077")
get_code_for_paper("2006.05077")
have("2006.05077")

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

curl https://syntology.ai/api/ran/2006.05077.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.05077.svg)](https://syntology.ai/paper/2006.05077)

Connect an agent — have() is free.