# Back to Simplicity: How to Train Accurate BNNs from Scratch? Source: [Back to Simplicity: How to Train Accurate BNNs from Scratch?]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:39:29.972Z Authors: Joseph Bethge, Haojin Yang, Marvin Bornstein, Christoph Meinel Published: 2019-06-19T10:32:45.000Z ## Abstract Binary Neural Networks (BNNs) show promising progress in reducing computational and memory costs but suffer from substantial accuracy degradation compared to their real-valued counterparts on large-scale datasets, e.g., ImageNet. Previous work mainly focused on reducing quantization errors of weights and activations, whereby a series of approximation methods and sophisticated training tricks have been proposed. In this work, we make several observations that challenge conventional wisdom. We revisit some commonly used techniques, such as scaling factors and custom gradients, and show that these methods are not crucial in training well-performing BNNs. On the contrary, we suggest several design principles for BNNs based on the insights learned and demonstrate that highly accurate BNNs can be trained from scratch with a simple training strategy. We propose a new BNN architecture BinaryDenseNet, which significantly surpasses all existing 1-bit CNNs on ImageNet without tricks. In our experiments, BinaryDenseNet achieves 18.6% and 7.6% relative improvement over the well-known XNOR-Network and the current state-of-the-art Bi-Real Net in terms of top-1 accuracy on ImageNet, respectively. ## 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. - [Object Detection on Pascal VOC (test)](): Object Detection; Pascal VOC (test); mAP: 68.2. - [Image Classification on ImageNet (val)](): Image Classification; ImageNet (val); Top-1 Acc: 58.1. ## Original sources and implementation [Original paper]() [PDF]()