# Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation Source: [Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:19:52.933Z Authors: Bohan Zhuang, Chunhua Shen, Mingkui Tan, Lingqiao Liu, Ian Reid Published: 2018-11-22T05:24:17.000Z ## Abstract In this paper, we propose to train convolutional neural networks (CNNs) with both binarized weights and activations, leading to quantized models specifically} for mobile devices with limited power capacity and computation resources. Previous works on quantizing CNNs seek to approximate the floating-point information using a set of discrete values, which we call value approximation, but typically assume the same architecture as the full-precision networks. In this paper, however, we take a novel 'structure approximation' view for quantization---it is very likely that a different architecture may be better for best performance. In particular, we propose a \`network decomposition' strategy, named \\textbf{Group-Net}, in which we divide the network into groups. In this way, each full-precision group can be effectively reconstructed by aggregating a set of homogeneous binary branches. In addition, we learn effective connections among groups to improve the representational capability. Moreover, the proposed Group-Net shows strong generalization to other tasks. For instance, we extend Group-Net for highly accurate semantic segmentation by embedding rich context into the binary structure. Experiments on both classification and semantic segmentation tasks demonstrate the superior performance of the proposed methods over various popular architectures. In particular, we outperform the previous best binary neural networks in terms of accuracy and major computation savings. ## 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. - [Semantic Segmentation on PASCAL VOC 2012 (val)](): Semantic segmentation; PASCAL VOC 2012 (val); Mean IoU: 60.5. ## Original sources and implementation [Original paper]() [PDF]()