Compact and Efficient Neural Networks for Image Recognition Based on Learned 2D Separable Transform

• URL: http://arxiv.org/abs/2505.06578v1
• Date: Sat, 10 May 2025 09:31:12 GMT
• Title: Compact and Efficient Neural Networks for Image Recognition Based on Learned 2D Separable Transform
• Authors: Maxim Vashkevich, Egor Krivalcevich,
• Abstract summary: The paper presents a learned two-dimensional separable transform (LST) that can be considered as a new type of computational layer for constructing neural network (NN) architecture for image recognition tasks.<n>We show that a NN-classifier based on a single LST layer followed by an FC layer achieves 98.02% accuracy on the MNIST dataset, while having only 9.5k parameters.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The paper presents a learned two-dimensional separable transform (LST) that can be considered as a new type of computational layer for constructing neural network (NN) architecture for image recognition tasks. The LST based on the idea of sharing the weights of one fullyconnected (FC) layer to process all rows of an image. After that, a second shared FC layer is used to process all columns of image representation obtained from the first layer. The use of LST layers in a NN architecture significantly reduces the number of model parameters compared to models that use stacked FC layers. We show that a NN-classifier based on a single LST layer followed by an FC layer achieves 98.02\% accuracy on the MNIST dataset, while having only 9.5k parameters. We also implemented a LST-based classifier for handwritten digit recognition on the FPGA platform to demonstrate the efficiency of the suggested approach for designing a compact and high-performance implementation of NN models. Git repository with supplementary materials: https://github.com/Mak-Sim/LST-2d

Related papers

• Tensor-to-Tensor Models with Fast Iterated Sum Features [3.1806397908898063]
  We propose a novel tensor-to-tensor layer with linear cost in the input size.<n>We provide an image-to-image layer that can be plugged into image processing pipelines.
  arXiv  Detail & Related papers  (2025-06-06T12:44:36Z)
• Tiled Bit Networks: Sub-Bit Neural Network Compression Through Reuse of Learnable Binary Vectors [4.95475852994362]
  We propose a new form of quantization to tile neural network layers with sequences of bits to achieve sub-bit compression of binary-weighted neural networks. We employ the approach to both fully-connected and convolutional layers, which make up the breadth of space in most neural architectures.
  arXiv  Detail & Related papers  (2024-07-16T15:55:38Z)
• SIMAP: A simplicial-map layer for neural networks [0.196629787330046]
  The SIMAP layer is an enhanced version of Simplicial-Map Neural Networks (SMNNs) Unlike SMNNs, the support set is based on a fixed maximal simplex, the barycentric subdivision being efficiently computed with a matrix-based multiplication algorithm.
  arXiv  Detail & Related papers  (2024-03-22T10:06:42Z)
• Pushing the Efficiency Limit Using Structured Sparse Convolutions [82.31130122200578]
  We propose Structured Sparse Convolution (SSC), which leverages the inherent structure in images to reduce the parameters in the convolutional filter. We show that SSC is a generalization of commonly used layers (depthwise, groupwise and pointwise convolution) in efficient architectures'' Architectures based on SSC achieve state-of-the-art performance compared to baselines on CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet classification benchmarks.
  arXiv  Detail & Related papers  (2022-10-23T18:37:22Z)
• Basis Scaling and Double Pruning for Efficient Inference in Network-Based Transfer Learning [1.3467579878240454]
  We decompose a convolutional layer into two layers: a convolutional layer with the orthonormal basis vectors as the filters, and a "BasisScalingConv" layer which is responsible for rescaling the features. We can achieve pruning ratios up to 74.6% for CIFAR-10 and 98.9% for MNIST in model parameters.
  arXiv  Detail & Related papers  (2021-08-06T00:04:02Z)
• ResMLP: Feedforward networks for image classification with data-efficient training [73.26364887378597]
  We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification. We will share our code based on the Timm library and pre-trained models.
  arXiv  Detail & Related papers  (2021-05-07T17:31:44Z)
• RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition [123.59890802196797]
  We propose RepMLP, a multi-layer-perceptron-style neural network building block for image recognition. We construct convolutional layers inside a RepMLP during training and merge them into the FC for inference. By inserting RepMLP in traditional CNN, we improve ResNets by 1.8% accuracy on ImageNet, 2.9% for face recognition, and 2.3% mIoU on Cityscapes with lower FLOPs.
  arXiv  Detail & Related papers  (2021-05-05T06:17:40Z)
• Evidential fully convolutional network for semantic segmentation [6.230751621285322]
  We propose a hybrid architecture composed of a fully convolutional network (FCN) and a Dempster-Shafer layer for image semantic segmentation. Experiments show that the proposed combination improves the accuracy and calibration of semantic segmentation by assigning confusing pixels to multi-class sets.
  arXiv  Detail & Related papers  (2021-03-25T01:21:22Z)
• Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling [79.15521784128102]
  We introduce a novel neural network for building image generators (decoders) and apply it to variational autoencoders (VAEs) In our spatial dependency networks (SDNs), feature maps at each level of a deep neural net are computed in a spatially coherent way. We show that augmenting the decoder of a hierarchical VAE by spatial dependency layers considerably improves density estimation.
  arXiv  Detail & Related papers  (2021-03-16T07:01:08Z)
• Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior [80.5637175255349]
  We propose a new enriched prior based Dual-constrained Deep Semi-Supervised Coupled Factorization Network, called DS2CF-Net. To ex-tract hidden deep features, DS2CF-Net is modeled as a deep-structure and geometrical structure-constrained neural network. Our network can obtain state-of-the-art performance for representation learning and clustering.
  arXiv  Detail & Related papers  (2020-09-08T13:10:21Z)
• Sparse Coding Driven Deep Decision Tree Ensembles for Nuclear Segmentation in Digital Pathology Images [15.236873250912062]
  We propose an easily trained yet powerful representation learning approach with performance highly competitive to deep neural networks in a digital pathology image segmentation task. The method, called sparse coding driven deep decision tree ensembles that we abbreviate as ScD2TE, provides a new perspective on representation learning.
  arXiv  Detail & Related papers  (2020-08-13T02:59:31Z)
• Convolutional Networks with Dense Connectivity [59.30634544498946]
  We introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks.
  arXiv  Detail & Related papers  (2020-01-08T06:54:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.