SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.12369 · ICCV · 2021

ReCU: Reviving the Dead Weights in Binary Neural Networks

Ling Shao, Jianzhuang Liu, Jie Chen, Yonghong Tian, Yue Gao, Rongrong Ji, Mingbao Lin, Zihan Xu

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 1 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/2103.12369.json · badge: /api/ran/2103.12369.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
stevetsui/rebnn community
Papers with Code archive
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
stevetsui/rbonn community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Binarization Ran
ran on a synthesized input · constructed an object; no result was computed
stevetsui/rebnn/2_step2_rebnn/rebnn.py
pointer only (licence: NONE) · get_code("688635f52b25f29c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, stevetsui/rebnn 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.

round_pass Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from stevetsui/rebnn
pointer only; the stored copy get_code serves, from stevetsui/rebnn, is pointer only (licence: NONE) · get_code("5111a3243a80feb0")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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.

RBOConv Not yet run
unverified (harvested, no recorded run)
stevetsui/rbonn/2_step2_rbonn/rbonn.py
pointer only (licence: NONE) · get_code("7d50863cee4ef06c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, stevetsui/rbonn 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 2 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
round_pass
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2003.03488 (2020-03)
ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions

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

Binary neural networks (BNNs) have received increasing attention due to their superior reductions of computation and memory. Most existing works focus on either lessening the quantization error by minimizing the gap between the full-precision weights and their binarization or designing a gradient approximation to mitigate the gradient mismatch, while leaving the "dead weights" untouched. This leads to slow convergence when training BNNs. In this paper, for the first time, we explore the influence of "dead weights" which refer to a group of weights that are barely updated during the training of BNNs, and then introduce rectified clamp unit (ReCU) to revive the "dead weights" for updating. We prove that reviving the "dead weights" by ReCU can result in a smaller quantization error. Besides, we also take into account the information entropy of the weights, and then mathematically analyze why the weight standardization can benefit BNNs. We demonstrate the inherent contradiction between minimizing the quantization error and maximizing the information entropy, and then propose an adaptive exponential scheduler to identify the range of the "dead weights". By considering the "dead weights", our method offers not only faster BNN training, but also state-of-the-art performance on CIFAR-10 and Im-ageNet, compared with recent methods. Code can be available at https://github.com/z-hXu/ReCU .

For agents

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

get_harvested_code_for_paper("2103.12369")
get_code_for_paper("2103.12369")
have("2103.12369")

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

curl https://syntology.ai/api/ran/2103.12369.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.12369.svg)](https://syntology.ai/paper/2103.12369)

Connect an agent — have() is free.