paper-with-me

홈 › Papers

Binarized Weight Error Networks With a Transition Regularization Term

2021-05-09 · Savas Ozkan, Gozde Bozdagi Akar

This paper proposes a novel binarized weight network (BT) for a resource-efficient neural structure. The proposed model estimates a binary representation of weights by taking into account the approximation error with an additional term. This model increases representation capacity and stability, particularly for shallow networks, while the computation load is theoretically reduced. In addition, a novel regularization term is introduced that is suitable for all threshold-based binary precision networks. This term penalizes the trainable parameters that are far from the thresholds at which binary transitions occur. This step promotes a swift modification for binary-precision responses at train time. The experimental results are carried out for two sets of tasks: visual classification and visual inverse problems. Benchmarks for Cifar10, SVHN, Fashion, ImageNet2012, Set5, Set14, Urban and BSD100 datasets show that our method outperforms all counterparts with binary precision.

📄 PDF Abstract BibTeX arXiv:2105.03897

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ProxyBNN: Learning Binarized Neural Networks via Proxy Matrices

2020-08-01 · ECCV 2020 8 · Xiangyu He, Zitao Mo, Ke Cheng, Weixiang Xu 외

Training Binarized Neural Networks (BNNs) is challenging due to the discreteness. In order to efficiently optimize BNNs through backward propagations, real-valued auxiliary variables are commonly used to accumulate gradi…

BinarizationQuantization

BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network

2024-05-27 · Zongkai Zhang, Zidong Xu, Wenming Yang, Qingmin Liao 외

Existing 3D occupancy networks demand significant hardware resources, hindering the deployment of edge devices. Binarized Neural Networks (BNN) offer substantially reduced computational and memory requirements. However, …

Binarization

Training Experimentally Robust and Interpretable Binarized Regression Models Using Mixed-Integer Programming

2021-12-01 · Sanjana Tule, Nhi Ha Lan Le, Buser Say

In this paper, we explore model-based approach to training robust and interpretable binarized regression models for multiclass classification tasks using Mixed-Integer Programming (MIP). Our MIP model balances the optimi…

Classificationregression

Toward Extremely Low Bit and Lossless Accuracy in DNNs with Progressive ADMM

2019-05-02 · Sheng Lin, Xiaolong Ma, Shaokai Ye, Geng Yuan 외

Weight quantization is one of the most important techniques of Deep Neural Networks (DNNs) model compression method. A recent work using systematic framework of DNN weight quantization with the advanced optimization algo…

Model CompressionQuantization

Fast Binarized Neural Network Training with Partial Pre-training

2021-01-01 · Alex Renda, Joshua Wolff Fromm

Binarized neural networks, networks with weights and activations constrained to lie in a 2-element set, allow for more time- and resource-efficient inference than standard floating-point networks. However, binarized neur…