SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.01404 · ECCV · 2022

Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies

Wei Li, Xianglong Liu, Jing Shao, Yangguang Li, Yufeng Wang, Xingrun Xing, Chunlei Liu, Wenrui Ding, Yalong Jiang

arXiv · PDF · Open in the Atlas

Code that ran

10 of 17 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 3 failures of our instrument; 7 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/2209.01404.json · badge: /api/ran/2209.01404.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
Sense-GVT/BCDNet community
Papers with Code archive
10 ran · 7 no recorded run
FunctionStatusWhere it lives
BinaryActivation Ran
ran on a synthesized input
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("576cf54b92fc2045")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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.

GlobalShift Ran
ran on a synthesized input · constructed an object; no result was computed
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("9f5b3152cc94a478")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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.

HardBinaryConv Ran
ran on a synthesized input
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("96414cb31453317f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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.

LearnableBias Ran
ran on a synthesized input · constructed an object; no result was computed
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("484fb153ec2ac5f4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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.

Shift Ran
ran on a synthesized input
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("ebd2689700cf8691")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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.

binaryconv1x1 Ran
ran; our contract draft was wrong, not the code
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("890ea919c4eae756")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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.

binaryconv3x3 Ran
ran; our contract draft was wrong, not the code
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("c8fd8f1b353d36a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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.

get_bn Ran
ran; our contract draft was wrong, not the code
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("8a98753263fba59d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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.

get_rank Ran
ran on a synthesized input
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("426074b9c7f8d0b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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.

get_world_size Ran
ran on a synthesized input
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("63a4bdc62e66305d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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.

BasicBlock Not yet run
unverified (harvested, no recorded run)
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("32055d142ffca233")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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. No invocation recorded.

Block Not yet run
unverified (harvested, no recorded run)
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("5468426c40c8c5bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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. No invocation recorded.

PointBlock Not yet run
unverified (harvested, no recorded run)
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("5b128936059e4741")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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. No invocation recorded.

Reactnet Not yet run
unverified (harvested, no recorded run)
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("c843b0dd7c6ad11c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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. No invocation recorded.

ShiftBlock Not yet run
unverified (harvested, no recorded run)
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("d0829f23d319c6c4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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. No invocation recorded.

firstconv3x3 Not yet run
unverified (harvested, no recorded run)
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("872a669394bfc1d1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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. No invocation recorded.

simple_group_split Not yet run
unverified (harvested, no recorded run)
Sense-GVT/BCDNet/prototype/model/a_3.py
pointer only (licence: NONE) · get_code("7bd0c3b833e49d56")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Sense-GVT/BCDNet 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. No invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 later) and 13 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
binaryconv3x3
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2102.08946 (2021-02)
S 2 -BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration
2201.07703 (2022-01)
Q-ViT: Fully Differentiable Quantization for Vision Transformer
BinaryActivation
brick of this paper's assembly: model
1 other paper
1 dated earlier · 1 only as an assembly brick
2102.08946 (2021-02)
S 2 -BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration
LearnableBias
brick of this paper's assembly: model
1 other paper
1 later
2305.10299 (2023-05)
Binarized Spectral Compressive Imaging
binaryconv1x1
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2102.08946 (2021-02)
S 2 -BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration

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

Existing Binary Neural Networks (BNNs) mainly operate on local convolutions with binarization function. However, such simple bit operations lack the ability of modeling contextual dependencies, which is critical for learning discriminative deep representations in vision models. In this work, we tackle this issue by presenting new designs of binary neural modules, which enables BNNs to learn effective contextual dependencies. First, we propose a binary multi-layer perceptron (MLP) block as an alternative to binary convolution blocks to directly model contextual dependencies. Both short-range and long-range feature dependencies are modeled by binary MLPs, where the former provides local inductive bias and the latter breaks limited receptive field in binary convolutions. Second, to improve the robustness of binary models with contextual dependencies, we compute the contextual dynamic embeddings to determine the binarization thresholds in general binary convolutional blocks. Armed with our binary MLP blocks and improved binary convolution, we build the BNNs with explicit Contextual Dependency modeling, termed as BCDNet. On the standard ImageNet-1K classification benchmark, the BCDNet achieves 72.3% Top-1 accuracy and outperforms leading binary methods by a large margin. In particular, the proposed BCDNet exceeds the state-of-the-art ReActNet-A by 2.9% Top-1 accuracy with similar operations. Our code is available at https://github.com/Sense-GVT/BCDNet.

For agents

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

get_harvested_code_for_paper("2209.01404")
get_code_for_paper("2209.01404")
have("2209.01404")

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

curl https://syntology.ai/api/ran/2209.01404.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.01404.svg)](https://syntology.ai/paper/2209.01404)

Connect an agent — have() is free.