Papers › Balanced Binary Neural Networks with Gated Residual

Balanced Binary Neural Networks with Gated Residual

26 Sep 2019arXiv:1909.12117archive 2025-07-28

Mingzhu Shen, Xianglong Liu, Ruihao Gong, Kai Han

Binary neural networks have attracted numerous attention in recent years. However, mainly due to the information loss stemming from the biased binarization, how to preserve the accuracy of networks still remains a critical issue. In this paper, we attempt to maintain the information propagated in the forward process and propose a Balanced Binary Neural Networks with Gated Residual (BBG for short). First, a weight balanced binarization is introduced to maximize information entropy of binary weights, and thus the informative binary weights can capture more information contained in the activations. Second, for binary activations, a gated residual is further appended to compensate their information loss during the forward process, with a slight overhead. Both techniques can be wrapped as a generic network module that supports various network architectures for different tasks including classification and detection. We evaluate our BBG on image classification tasks over CIFAR-10/100 and ImageNet and on detection task over Pascal VOC. The experimental results show that BBG-Net performs remarkably well across various network architectures such as VGG, ResNet and SSD with the superior performance over state-of-the-art methods in terms of memory consumption, inference speed and accuracy.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

JDAI-CV/dabnn mentioned on GitHubNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

BinarizationGeneral ClassificationImage Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet BBG (ResNet-34) Top 1 Accuracy 62.6% #1050 of 1060 Archive leaderboard report
Image Classification ImageNet BBG (ResNet-18) Top 1 Accuracy 59.4% #1052 of 1060 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsDropoutGlobal Average PoolingKaiming InitializationMax PoolingNon Maximum SuppressionReLUResidual BlockResidual ConnectionSPEEDSSDSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections