# Binary Input Layer: Training of CNN models with binary input data

arXiv: https://arxiv.org/abs/1812.03410 · HTML: https://mlsanity.com/paper/1812.03410/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2018.

## Built on by (most cited first, 4 of 4)

- [Input Layer Binarization with Bit-Plane Encoding](https://mlsanity.com/paper/2305.02885/) (2023)
- [Pixel Embedding: Fully Quantized Convolutional Neural Network with Differentiable Lookup Table](https://mlsanity.com/paper/2407.16174/) (2024)
- [Efficiera Residual Networks: Hardware-Friendly Fully Binary Weight with 2-bit Activation Model Achieves Practical ImageNet Accuracy](https://mlsanity.com/paper/2410.11553/) (2024)
- [End-to-end fully-binarized network design: from Generic Learned Thermometer to Block Pruning](https://mlsanity.com/paper/2505.13462/) (2025)

## Abstract (arXiv)

For the efficient execution of deep convolutional neural networks (CNN) on edge devices, various approaches have been presented which reduce the bit width of the network parameters down to 1 bit. Binarization of the first layer was always excluded, as it leads to a significant error increase. Here, we present the novel concept of binary input layer (BIL), which allows the usage of binary input data by learning bit specific binary weights. The concept is evaluated on three datasets (PAMAP2, SVHN, CIFAR-10). Our results show that this approach is in particular beneficial for multimodal datasets (PAMAP2) where it outperforms networks using full precision weights in the first layer by 1:92 percentage points (pp) while consuming only 2 % of the chip area.