# Towards Accurate Binary Convolutional Neural Network Source: [Towards Accurate Binary Convolutional Neural Network]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:51:10.308Z Authors: Xiaofan Lin, Cong Zhao, Wei Pan Published: 2017-11-30T09:58:14.000Z ## Abstract We introduce a novel scheme to train binary convolutional neural networks (CNNs) -- CNNs with weights and activations constrained to {-1,+1} at run-time. It has been known that using binary weights and activations drastically reduce memory size and accesses, and can replace arithmetic operations with more efficient bitwise operations, leading to much faster test-time inference and lower power consumption. However, previous works on binarizing CNNs usually result in severe prediction accuracy degradation. In this paper, we address this issue with two major innovations: (1) approximating full-precision weights with the linear combination of multiple binary weight bases; (2) employing multiple binary activations to alleviate information loss. The implementation of the resulting binary CNN, denoted as ABC-Net, is shown to achieve much closer performance to its full-precision counterpart, and even reach the comparable prediction accuracy on ImageNet and forest trail datasets, given adequate binary weight bases and activations. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on ImageNet 1k (val) (Top-1/Top-5 Accuracy)](): Image Classification; ImageNet-1k (val); Top-1 Acc: 65. - [Image Classification on ImageNet (val)](): Image Classification; ImageNet (val); Top-1 Acc: 42.7. ## Original sources and implementation [Original paper]() [PDF]()