Classification with Binary Neural Network

7 papers with code • 3 benchmarks • 3 datasets

This task has no description! Would you like to contribute one?


Use these libraries to find Classification with Binary Neural Network models and implementations

Most implemented papers

XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

hpi-xnor/BMXNet 16 Mar 2016

We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks.

AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets

huawei-noah/Efficient-Computing 17 Aug 2022

Since the modern deep neural networks are of sophisticated design with complex architecture for the accuracy reason, the diversity on distributions of weights and activations is very high.

Improved training of binary networks for human pose estimation and image recognition

1adrianb/binary-networks-pytorch 11 Apr 2019

Big neural networks trained on large datasets have advanced the state-of-the-art for a large variety of challenging problems, improving performance by a large margin.

XNOR-Net++: Improved Binary Neural Networks

1adrianb/binary-networks-pytorch 30 Sep 2019

This paper proposes an improved training algorithm for binary neural networks in which both weights and activations are binary numbers.

Training Binary Neural Networks with Real-to-Binary Convolutions

brais-martinez/real2binary ICLR 2020

This paper shows how to train binary networks to within a few percent points ($\sim 3-5 \%$) of the full precision counterpart.

High-Capacity Expert Binary Networks

1adrianb/expert-binary-networks ICLR 2021

Network binarization is a promising hardware-aware direction for creating efficient deep models.

Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network

chrundle/biprop 17 Mar 2021

In this paper, we propose (and prove) a stronger Multi-Prize Lottery Ticket Hypothesis: A sufficiently over-parameterized neural network with random weights contains several subnetworks (winning tickets) that (a) have comparable accuracy to a dense target network with learned weights (prize 1), (b) do not require any further training to achieve prize 1 (prize 2), and (c) is robust to extreme forms of quantization (i. e., binary weights and/or activation) (prize 3).