mlsanityData to 14 Oct 2026

A Tensor-based Convolutional Neural Network for Small Dataset Classification

arXiv 2303.17061 ↗First posted 29 Mar 2023cs.CV cs.GTcited by 0

Not on the map. Why?

Abstract (arXiv)

Inspired by the ConvNets with structured hidden representations, we propose a Tensor-based Neural Network, TCNN. Different from ConvNets, TCNNs are composed of structured neurons rather than scalar neurons, and the basic operation is neuron tensor transformation. Unlike other structured ConvNets, where the part-whole relationships are modeled explicitly, the relationships are learned implicitly in TCNNs. Also, the structured neurons in TCNNs are high-rank tensors rather than vectors or matrices. We compare TCNNs with current popular ConvNets, including ResNets, MobileNets, EfficientNets, RegNets, etc., on CIFAR10, CIFAR100, and Tiny ImageNet. The experiment shows that TCNNs have higher efficiency in terms of parameters. TCNNs also show higher robustness against white-box adversarial attacks on MNIST compared to ConvNets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 37 references that are in the map. First posted on arXiv 29 Mar 2023.

Builds on

26 of 37 references.

References · 26

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  6. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  7. 2022A ConvNet for the 2020scited by 3,579
  8. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  9. 2015Spatial Transformer Networkscited by 1,429
  10. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
  11. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  12. 2020Designing Network Design Spacescited by 960
14 more
  1. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  2. 2017Dynamic Routing Between Capsulescited by 689
  3. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  4. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 378
  5. 2018NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applicationscited by 147
  6. 2019Provable Filter Pruning for Efficient Neural Networkscited by 98
  7. 2020Bayesian Bits: Unifying Quantization and Pruningcited by 94
  8. 2019DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measurescited by 56
  9. 2021Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Searchcited by 34
  10. 2020Architectural Adversarial Robustness: The Case for Deep Pursuitcited by 18
  11. 2019Attention routing between capsulescited by 17
  12. 2018Adversarial Noise Attacks of Deep Learning Architectures -- Stability Analysis via Sparse Modeled Signalscited by 9
  13. 2018Dense and Diverse Capsule Networks: Making the Capsules Learn Bettercited by 6
  14. 2020PENNI: Pruned Kernel Sharing for Efficient CNN Inferencecited by 6

Built on by

Not cited yet.