paper-with-me

홈 › Papers

Self-Distribution Binary Neural Networks

2021-03-03 · Ping Xue, Yang Lu, Jingfei Chang, Xing Wei, Zhen Wei

In this work, we study the binary neural networks (BNNs) of which both the weights and activations are binary (i.e., 1-bit representation). Feature representation is critical for deep neural networks, while in BNNs, the features only differ in signs. Prior work introduces scaling factors into binary weights and activations to reduce the quantization error and effectively improves the classification accuracy of BNNs. However, the scaling factors not only increase the computational complexity of networks, but also make no sense to the signs of binary features. To this end, Self-Distribution Binary Neural Network (SD-BNN) is proposed. Firstly, we utilize Activation Self Distribution (ASD) to adaptively adjust the sign distribution of activations, thereby improve the sign differences of the outputs of the convolution. Secondly, we adjust the sign distribution of weights through Weight Self Distribution (WSD) and then fine-tune the sign distribution of the outputs of the convolution. Extensive experiments on CIFAR-10 and ImageNet datasets with various network structures show that the proposed SD-BNN consistently outperforms the state-of-the-art (SOTA) BNNs (e.g., achieves 92.5% on CIFAR-10 and 66.5% on ImageNet with ResNet-18) with less computation cost. Code is available at https://github.com/ pingxue-hfut/SD-BNN.

📄 PDF Abstract BibTeX arXiv:2103.02394

Code (1)

pingxue-hfut/sd-bnn 공식 구현 pytorch

Tasks

Quantization

Similar Papers 제목 키워드 기반

DLBD: A Self-Supervised Direct-Learned Binary Descriptor

2023-01-01 · CVPR 2023 1 · Bin Xiao, Yang Hu, Bo Liu, Xiuli Bi 외

For learning-based binary descriptors, the binarization process has not been well addressed. The reason is that the binarization blocks gradient back-propagation. Existing learning-based binary descriptors learn real…

BinarizationImage RetrievalRetrieval

Binary Search with Distributional Predictions

2024-11-25 · Michael Dinitz, Sungjin Im, Thomas Lavastida, Benjamin Moseley 외

Algorithms with (machine-learned) predictions is a powerful framework for combining traditional worst-case algorithms with modern machine learning. However, the vast majority of work in this space assumes that the predic…

Prediction

FBPT: A Fully Binary Point Transformer

2024-03-15 · Zhixing Hou, Yuzhang Shang, Yan Yan

This paper presents a novel Fully Binary Point Cloud Transformer (FBPT) model which has the potential to be widely applied and expanded in the fields of robotics and mobile devices. By compressing the weights and activat…

BinarizationPoint Cloud Classification

S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration

2021-02-17 · CVPR 2021 1 · Zhiqiang Shen, Zechun Liu, Jie Qin, Lei Huang 외

Previous studies dominantly target at self-supervised learning on real-valued networks and have achieved many promising results. However, on the more challenging binary neural networks (BNNs), this task has not yet been …

Contrastive LearningSelf-Supervised Learning

Binary Self-Selective Voting Rules

2025-06-18 · Héctor Hermida-Rivera, Toygar T. Kerman

This paper introduces a novel binary stability property for voting rules-called binary self-selectivity-by which a society considering whether to replace its voting rule using itself in pairwise elections will choose not…