pith. sign in

arxiv: 1603.05279 · v4 · pith:WD2T554Cnew · submitted 2016-03-16 · 💻 cs.CV

XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

Mohammad Rastegari , Vicente Ordonez , Joseph Redmon , Ali Farhadi This is my paper
classification 💻 cs.CV
keywords binaryconvolutionalnetworksclassificationimagenetxnor-networksaccuracyalexnet
0
0 comments X
read the original abstract

We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary values resulting in 32x memory saving. In XNOR-Networks, both the filters and the input to convolutional layers are binary. XNOR-Networks approximate convolutions using primarily binary operations. This results in 58x faster convolutional operations and 32x memory savings. XNOR-Nets offer the possibility of running state-of-the-art networks on CPUs (rather than GPUs) in real-time. Our binary networks are simple, accurate, efficient, and work on challenging visual tasks. We evaluate our approach on the ImageNet classification task. The classification accuracy with a Binary-Weight-Network version of AlexNet is only 2.9% less than the full-precision AlexNet (in top-1 measure). We compare our method with recent network binarization methods, BinaryConnect and BinaryNets, and outperform these methods by large margins on ImageNet, more than 16% in top-1 accuracy.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

    cs.CV 2017-04 accept novelty 7.0

    MobileNets introduce depthwise separable convolutions plus width and resolution multipliers to produce efficient CNNs that trade off latency and accuracy for mobile and embedded vision applications.

  2. Co-Evolutionary Compression for Unpaired Image Translation

    cs.CV 2019-07 unverdicted novelty 6.0

    A co-evolutionary compression technique reduces parameters and FLOPs in unpaired image-to-image translation GAN generators while maintaining translation quality on benchmarks.

  3. Single-bit-per-weight deep convolutional neural networks without batch-normalization layers for embedded systems

    cs.LG 2019-07 unverdicted novelty 4.0

    Experiments show that shifted-ReLU layers can replace batch-normalization in single-bit-weight wide residual networks on CIFAR-10/100 and ImageNet without consistent accuracy penalty.

  4. How much real data do we actually need: Analyzing object detection performance using synthetic and real data

    cs.CV 2019-07 unverdicted novelty 3.0

    Synthetic data can partially substitute for real data in object detection training, with performance tied to domain similarity and the volume of real data included.