mlsanityData to 7 Oct 2026

Tensor Yard: One-Shot Algorithm of Hardware-Friendly Tensor-Train Decomposition for Convolutional Neural Networks

arXiv 2108.04029 ↗First posted 9 Aug 2021cs.CV cs.ARcited by 3

Not on the map. Why?

Abstract (arXiv)

Nowadays Deep Learning became widely used in many economic, technical and scientific areas of human interest. It is clear that efficiency of solutions based on Deep Neural Networks should consider not only quality metric for the target task, but also latency and constraints of target platform design should be taken into account. In this paper we present novel hardware-friendly Tensor-Train decomposition implementation for Convolutional Neural Networks together with Tensor Yard - one-shot training algorithm which optimizes an order of decomposition of network layers. These ideas allow to accelerate ResNet models on Ascend 310 NPU devices without significant loss of accuracy. For example we accelerate ResNet-101 by 14.6% with drop by 0.5 of top-1 ImageNet accuracy.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 13 of its 23 references that are in the map. First posted on arXiv 9 Aug 2021.

Builds on

13 of 23 references.

References · 13

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  4. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  5. 2018Soft Filter Pruning for Accelerating Deep Convolutional Neural Networkscited by 313
  6. 2015Tensorizing Neural Networkscited by 246
  7. 2019Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluationcited by 230
  8. 2014Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decompositioncited by 199
  9. 2015Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applicationscited by 161
  10. 2016Ultimate tensorization: compressing convolutional and FC layers alikecited by 55
  11. 2018Wide Compression: Tensor Ring Netscited by 50
  12. 2019Bayesian Tensorized Neural Networks with Automatic Rank Selectioncited by 24
1 more
  1. 2019MUSCO: Multi-Stage Compression of neural networkscited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 0; 2023: 0; 2024: 1; 2025: 1.

3 papers.

  1. 2025Tensorization is a powerful but underexplored tool for compression and interpretability of neural networkscited by 3
  2. 2021ISyNet: Convolutional Neural Networks design for AI acceleratorcited by 1
  3. 2024Layer-Specific Optimization: Sensitivity Based Convolution Layers Basis Searchcited by 0