mlsanityData to 14 Oct 2026

Binarized Weight Error Networks With a Transition Regularization Term

arXiv 2105.03897 ↗First posted 9 May 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 24 references that are in the map. First posted on arXiv 9 May 2021.

Builds on

18 of 24 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  4. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  5. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  6. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  7. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  8. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 569
  9. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 426
  10. 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 274
  11. 2016Trained Ternary Quantizationcited by 208
  12. 2016Ternary Weight Networkscited by 204
6 more
  1. 2020Binary Neural Networks: A Surveycited by 190
  2. 2019Quantization Networkscited by 153
  3. 2016Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1cited by 105
  4. 2018Efficient Super Resolution Using Binarized Neural Networkcited by 29
  5. 2020Resource-Efficient Neural Networks for Embedded Systemscited by 20
  6. 2020Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and Latencycited by 16

Built on by

Not cited yet.