mlsanityData to 7 Oct 2026

DCFNet: Deep Neural Network with Decomposed Convolutional Filters

arXiv 1802.04145 ↗First posted 12 Feb 2018stat.ML cs.CV cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

Filters in a Convolutional Neural Network (CNN) contain model parameters learned from enormous amounts of data. In this paper, we suggest to decompose convolutional filters in CNN as a truncated expansion with pre-fixed bases, namely the Decomposed Convolutional Filters network (DCFNet), where the expansion coefficients remain learned from data. Such a structure not only reduces the number of trainable parameters and computation, but also imposes filter regularity by bases truncation. Through extensive experiments, we consistently observe that DCFNet maintains accuracy for image classification tasks with a significant reduction of model parameters, particularly with Fourier-Bessel (FB) bases, and even with random bases. Theoretically, we analyze the representation stability of DCFNet with respect to input variations, and prove representation stability under generic assumptions on the expansion coefficients. The analysis is consistent with the empirical observations.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 2; 2023: 5; 2024: 8; 2025: 3.

23 papers.

Sort:

By area:

  1. 2024Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimizationcited by 25
  2. 2021Adaptive Convolutions with Per-pixel Dynamic Filter Atomcited by 11
  3. 2024Large Convolutional Model Tuning via Filter Subspacecited by 11
  4. 2022ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learningcited by 9
  5. 2024TriNeRFLet: A Wavelet Based Triplane NeRF Representationcited by 8
  6. 2021Deformation Robust Roto-Scale-Translation Equivariant CNNscited by 7
  7. 2024Tilt your Head: Activating the Hidden Spatial-Invariance of Classifierscited by 7
  8. 2021unzipFPGA: Enhancing FPGA-based CNN Engines with On-the-Fly Weights Generationcited by 4
  9. 2021Phase Collapse in Neural Networkscited by 4
  10. 2023The Power of Linear Combinations: Learning with Random Convolutionscited by 4
  11. 2023Learning Kernel-Modulated Neural Representation for Efficient Light Field Compressioncited by 2
  12. 2025Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Modelscited by 2
11 more
  1. 2022CoShNet: A Hybrid Complex Valued Neural Network using Shearletscited by 1
  2. 2023Adaptive aggregation of Monte Carlo augmented decomposed filters for efficient group-equivariant convolutional neural networkcited by 1
  3. 2023Mitigating Memory Wall Effects in CNN Engines with On-the-Fly Weights Generationcited by 1
  4. 2024Generative Quanta Color Imagingcited by 1
  5. 2025Sparse Fine-Tuning of Transformers for Generative Taskscited by 1
  6. 2021AdjointBackMapV2: Precise Reconstruction of Arbitrary CNN Unit's Activation via Adjoint Operatorscited by 0
  7. 2023Learning-based Spatial and Angular Information Separation for Light Field Compressioncited by 0
  8. 2024Efficient 3D affinely equivariant CNNs with adaptive fusion of augmented spherical Fourier-Bessel basescited by 0
  9. 2024Boosting Medical Image Segmentation Performance with Adaptive Convolution Layercited by 0
  10. 2024Stability Analysis of Equivariant Convolutional Representations Through The Lens of Equivariant Multi-layered CKNscited by 0
  11. 2025Extra Clients at No Extra Cost: Overcome Data Heterogeneity in Federated Learning with Filter Decompositioncited by 0