SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.02720 · ICCV · 2021

Generalizable Mixed-Precision Quantization via Attribution Rank Preservation

Jiwen Lu, Jie Zhou, Ziwei Wang, Han Xiao

arXiv · PDF · Open in the Atlas

Code that ran

None of the 9 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (9 no recorded run), measured 2026-11-22; 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/2108.02720.json · badge: /api/ran/2108.02720.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
ZiweiWangTHU/GMPQ marked official in Papers with Code
Papers with Code archive
0 ran · 9 no recorded run
FunctionStatusWhere it lives
MixActivConv2d Not yet run
unverified (harvested, no recorded run)
ZiweiWangTHU/GMPQ/models/quant_module.py
code served (permissive licence) · get_code("6c543b08a51e1807")
How it ran

no invocation recorded.

MixQuantActiv Not yet run
unverified (harvested, no recorded run)
ZiweiWangTHU/GMPQ/models/quant_module.py
code served (permissive licence) · get_code("38ac64e2ffccc79f")
How it ran

no invocation recorded.

MixQuantConv2d Not yet run
unverified (harvested, no recorded run)
ZiweiWangTHU/GMPQ/models/quant_module.py
code served (permissive licence) · get_code("32a3a373a61f1896")
How it ran

no invocation recorded.

QModule Not yet run
unverified (harvested, no recorded run)
ZiweiWangTHU/GMPQ/models/quant_module.py
code served (permissive licence) · get_code("6e5ee002fef7d9bc")
How it ran

no invocation recorded.

QuantActiv Not yet run
unverified (harvested, no recorded run)
ZiweiWangTHU/GMPQ/models/quant_module.py
code served (permissive licence) · get_code("83c4b6d54fdedef0")
How it ran

no invocation recorded.

QuantConv Not yet run
unverified (harvested, no recorded run)
ZiweiWangTHU/GMPQ/models/quant_module.py
code served (permissive licence) · get_code("a780e836b4430895")
How it ran

no invocation recorded.

STE Not yet run
unverified (harvested, no recorded run)
ZiweiWangTHU/GMPQ/models/quant_module.py
code served (permissive licence) · get_code("0576ea76dd26fcd6")
How it ran

no invocation recorded.

SharedMixQuantConv2d Not yet run
unverified (harvested, no recorded run)
ZiweiWangTHU/GMPQ/models/quant_module.py
code served (permissive licence) · get_code("ee2ba6d38e71a370")
How it ran

no invocation recorded.

calibrate Not yet run
unverified (harvested, no recorded run)
ZiweiWangTHU/GMPQ/models/quant_module.py
code served (permissive licence) · get_code("8d472ac9cdab47d3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 9 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.

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 this paper, we propose a generalizable mixedprecision quantization (GMPQ) method for efficient inference. Conventional methods require the consistency of datasets for bitwidth search and model deployment to guarantee the policy optimality, leading to heavy search cost on challenging largescale datasets in realistic applications. On the contrary, our GMPQ searches the mixedquantization policy that can be generalized to largescale datasets with only a small amount of data, so that the search cost is significantly reduced without performance degradation. Specifically, we observe that locating network attribution correctly is general ability for accurate visual analysis across different data distribution. Therefore, despite of pursuing higher model accuracy and complexity, we preserve attribution rank consistency between the quantized models and their full-precision counterparts via efficient capacity-aware attribution imitation for generalizable mixed-precision quantization strategy search. Extensive experiments show that our method obtains competitive accuracy-complexity trade-off compared with the state-of-the-art mixed-precision networks in significantly reduced search cost. The code is available at https://github.com/ZiweiWangTHU/GMPQ.git.

For agents

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

get_harvested_code_for_paper("2108.02720")
get_code_for_paper("2108.02720")
have("2108.02720")

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

curl https://syntology.ai/api/ran/2108.02720.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.02720.svg)](https://syntology.ai/paper/2108.02720)

Connect an agent — have() is free.