Pith. sign in

REVIEW 6 cited by

Demystifying Neural Style Transfer

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1701.01036 v2 pith:4KGFFEOO submitted 2017-01-04 cs.CV cs.LGcs.NE

Yanghao Li , Naiyan Wang , Jiaying Liu , Xiaodi Hou This is my paper · ORCID
classification cs.CVcs.LGcs.NE
keywords styleneuraltransferresultsfeaturegramimagesinterpretation
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Neural Style Transfer has recently demonstrated very exciting results which catches eyes in both academia and industry. Despite the amazing results, the principle of neural style transfer, especially why the Gram matrices could represent style remains unclear. In this paper, we propose a novel interpretation of neural style transfer by treating it as a domain adaptation problem. Specifically, we theoretically show that matching the Gram matrices of feature maps is equivalent to minimize the Maximum Mean Discrepancy (MMD) with the second order polynomial kernel. Thus, we argue that the essence of neural style transfer is to match the feature distributions between the style images and the generated images. To further support our standpoint, we experiment with several other distribution alignment methods, and achieve appealing results. We believe this novel interpretation connects these two important research fields, and could enlighten future researches.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Recognizing Artistic Style of Archaeological Image Fragments Using Deep Style Extrapolation

    cs.CV 2025-01 conditional novelty 6.0 of 10

    A style extrapolation module followed by a transfer-learned classifier achieves state-of-the-art artistic style recognition on archaeological image fragments, validated on a new Pompeii fresco fragment dataset.

  2. How Sequence-to-Sequence Models Perceive Language Styles?

    cs.CL 2019-08 conditional novelty 6.0 of 10

    Style in text is represented by the covariance matrix of seq2seq semantic vectors, enabling a whitening-coloring style transfer algorithm.

  3. Through Van Gogh's Eyes: Global Style Transfer with Diffusion Model

    cs.CV 2026-08 conditional novelty 5.0 of 10

    The paper proposes Global Style Transfer, which trains a residual style offset in the h-space of a diffusion model on many artworks of one artist and applies it to new content images, aiming for artist-level rather th...

  4. Contrastive Desensitization Learning for Cross Domain Face Forgery Detection

    cs.CV 2025-05 reject novelty 5.0 of 10

    CDN mixes feature statistics of genuine face images and reconstructs them to reduce false alarms in cross-domain deepfake detection, but the supporting theory is flawed and the artifacts are missing.

  5. Demystifying Brain Tumour Segmentation Networks: Interpretability and Uncertainty Analysis

    eess.IV 2019-09 conditional novelty 4.0 of 10

    Applying network dissection, Grad-CAM, activation maximization, and test-time dropout to three 2D brain tumor segmentation networks suggests filter-level concepts and coarse-to-fine localization, with high uncertainty...

  6. STaDA: Style Transfer as Data Augmentation

    cs.CV 2019-09 reject novelty 4.0 of 10

    STaDA applies neural style transfer as a data augmentation method for image classification, reporting up to 2% accuracy improvement on Caltech 101 with VGG16, though the effect varies strongly by style.

Pith tools