Methods › General › Regularization › Orthogonal Regularization

Orthogonal Regularization

27 papers tagged archive 2025-07-28

Introduced by Andrew Brock et al. in Neural Photo Editing with Introspective Adversarial Networks

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Orthogonal Regularization is a regularization technique for convolutional neural networks, introduced with generative modelling as the task in mind. Orthogonality is argued to be a desirable quality in ConvNet filters, partially because multiplication by an orthogonal matrix leaves the norm of the original matrix unchanged. This property is valuable in deep or recurrent networks, where repeated matrix multiplication can result in signals vanishing or exploding. To try to maintain orthogonality throughout training, Orthogonal Regularization encourages weights to be orthogonal by pushing them towards the nearest orthogonal manifold. The objective function is augmented with the cost:

ℒₒᵣₜₕₒ = ∑(|WWᵀ − I|)

Where ∑ indicates a sum across all filter banks, W is a filter bank, and I is the identity matrix

PaperSourceSee Code · pytorch/pytorch

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: Orthogonality Regularization; Orthogonal Jacobian Regularization (OroJaR); Orthogonal Decoupling Contrastive Regularization (ODCR); Orthogonal JEPA; orthogonal growth; cost regularization; regularization loss; Path Regularization.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 27 · with a code link: 17 · where Syntology ran a sample: 6 (6 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (6 of 27 tagged: 6 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 27 of 27, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 52 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Image Classification3
Image Generation3
Data Augmentation2
Dimensionality Reduction2
Federated Learning2
General Classification2
Model Compression2
Sentence2
Sentiment Analysis2
Speech Synthesis2
Video Generation2
Video Prediction2
Vocal Bursts Intensity Prediction2
image-classification2
3D Character Animation From A Single Photo1
Articles1
Aspect-Based Sentiment Analysis1
Aspect-Based Sentiment Analysis (ABSA)1
Attribute1
Classification1

Usage over time archive 2025-07-28

Papers per year tagged with Orthogonal Regularization: 2016 to 2025, peak 6 6 0 2016: 1 paper 2016 2017: 0 papers 2017 2018: 2 papers 2018 2019: 3 papers 2019 2020: 5 papers 2020 2021: 3 papers 2021 2022: 3 papers 2022 2023: 3 papers 2023 2024: 6 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (27 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Regularization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections