SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.06875 · CVPR · 2021

Multi-Scale Aligned Distillation for Low-Resolution Detection

Hong Kong, Yanwei Li, Jiaya Jia, Jiuxiang Gu, Jason Kuen, Yukang Chen, Yi Wang, Lu Qi, Zhe Lin

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 0 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/2109.06875.json · badge: /api/ran/2109.06875.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
Jia-Research-Lab/MSAD marked official in Papers with Code
Papers with Code archive
4 ran · 0 no recorded run
FunctionStatusWhere it lives
EPE Ran
ran, honoured the contract we drafted
Jia-Research-Lab/MSAD/msad/layers/loss.py
pointer only (licence: NONE) · get_code("6baff9bff3755d04")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Jia-Research-Lab/MSAD when it was checked. 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.

L1 Ran
ran on a synthesized input
Jia-Research-Lab/MSAD/msad/layers/loss.py
pointer only (licence: NONE) · get_code("5f22bd913308e42f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Jia-Research-Lab/MSAD when it was checked. 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.

L2 Ran
ran on a synthesized input
Jia-Research-Lab/MSAD/msad/layers/loss.py
pointer only (licence: NONE) · get_code("b0e79cd4dedcd4e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Jia-Research-Lab/MSAD when it was checked. 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.

MultiScale Ran
ran on a synthesized input · constructed an object; no result was computed
Jia-Research-Lab/MSAD/msad/layers/loss.py
pointer only (licence: NONE) · get_code("0d75b5053b3b0641")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Jia-Research-Lab/MSAD when it was checked. 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.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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, 1 later) and 3 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
EPE
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later
2005.10954 (2020-05)
Head2Head: Video-based Neural Head Synthesis
2308.13133 (2023-08)
AccFlow: Backward Accumulation for Long-Range Optical Flow

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

In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting performance of low-resolution models by distilling knowledge from a high-or multi-resolution model. We first identify the challenge of applying knowledge distillation (KD) to teacher and student networks that act on different input resolutions. To tackle it, we explore the idea of spatially aligning feature maps between models of varying input resolutions by shifting feature pyramid position and introduce aligned multi-scale training to train a multi-scale teacher that can distill its knowledge to a low-resolution student. Further, we propose crossing feature-level fusion to dynamically fuse teacher's multi-resolution features to guide the student better. On several instance-level detection tasks and datasets, the low-resolution models trained via our approach perform competitively with high-resolution models trained via conventional multi-scale training, while outperforming the latter's low-resolution models by 2.1% to 3.6% in terms of mAP. Our code is made publicly available

For agents

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

get_harvested_code_for_paper("2109.06875")
get_code_for_paper("2109.06875")
have("2109.06875")

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

curl https://syntology.ai/api/ran/2109.06875.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.06875.svg)](https://syntology.ai/paper/2109.06875)

Connect an agent — have() is free.