MétaCan
Menu
Back to cohort
Record W4387129549 · doi:10.1109/access.2023.3320642

Frequency Regularization: Reducing Information Redundancy in Convolutional Neural Networks

2023· article· en· W4387129549 on OpenAlexaff
Chenqiu Zhao, Guanfang Dong, Shupei Zhang, Zijie Tan, Anup Basu

Bibliographic record

VenueIEEE Access · 2023
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Neural Network Applications
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsFrequency domainRegularization (linguistics)Computer scienceConvolutional neural networkRedundancy (engineering)AlgorithmArtificial neural networkReduction (mathematics)Pattern recognition (psychology)Artificial intelligenceMathematicsComputer vision

Abstract

fetched live from OpenAlex

Convolutional neural networks have demonstrated impressive results in many computer vision tasks. However, the increasing size of these networks raises concerns about the information overload resulting from the large number of network parameters. In this paper, we propose Frequency Regularization to restrict the non-zero elements of the network parameters in the frequency domain. The proposed approach operates at the tensor level, and can be applied to almost all network architectures. Specifically, the tensors of parameters are maintained in the frequency domain, where high-frequency components can be eliminated by zigzag setting tensor elements to zero. Then, the inverse discrete cosine transform (IDCT) is used to reconstruct the spatial tensors for matrix operations during network training. Since high-frequency components of images are known to be less critical, a large proportion of these parameters can be set to zero when networks are trained with the proposed frequency regularization. Comprehensive evaluations on various state-of-the-art network architectures, including LeNet, Alexnet, VGG, Resnet, ViT, UNet, GAN, and VAE, demonstrate the effectiveness of the proposed frequency regularization. For a very small accuracy decrease (less than 2%), a LeNet5 with 0.4M parameters can be represented by only 776 float16 numbers (over 1100× reduction), and a UNet with 34M parameters can be represented by only 759 float16 numbers (over 80000× reduction). In particular, the original size of the UNet model is reduced from 366 Mb to 4.5 Kb.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.959
Threshold uncertainty score0.541

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.003
Science and technology studies0.0000.000
Scholarly communication0.0000.005
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.027
GPT teacher head0.295
Teacher spread0.268 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations6
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueIEEE AccessSame topicAdvanced Neural Network ApplicationsFrench-language works237,207