Skip to content
AI News HubLIVE
Original source3 min read

Scoring, Not Learning: Decomposing Catalog-Consolidation Gains in Web-Scraped Retail Product Recognition

Summary

A new paper shows that consolidating web-scraped retail product catalogs yields accuracy gains primarily from changing the evaluation label space, not from improved model learning.

SourcearXiv Computer VisionAuthor: Kaden Leis, Xiang Ma
Scoring, Not Learning: Decomposing Catalog-Consolidation Gains in Web-Scraped Retail Product Recognition
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 5 Nov 2026]

Title:Scoring, Not Learning: Decomposing Catalog-Consolidation Gains in Web-Scraped Retail Product Recognition

View a PDF of the paper titled Scoring, Not Learning: Decomposing Catalog-Consolidation Gains in Web-Scraped Retail Product Recognition, by Kaden Leis and 1 other authors

View PDF HTML (experimental)

Abstract:Retail product catalogs assembled from web image search are cheap to build and pervasively noisy: queries return packaging shots instead of products, and entries proliferate under names that cannot be distinguished visually. Consolidating such a catalog can look like an alternative to scaling the model. We show this is not a comparison between two ways of improving a recognizer, but between improving a recognizer and changing what counts as correct. We study a public archive of 165,769 cheese images across 1,824 query-named entries. A packaging filter and near-duplicate removal reduce it to a 998-class recognition set on one fixed, group-aware split. Canonicalizing entries to their base type (844 classes) raises top-1 accuracy by 4.0 points. Scoring the unchanged model against the merged label space, by summing its predicted probability within each canonical group, recovers +4.27 points with no retraining (+4.25 over six seeds). Retraining on the consolidated catalog then adds -0.10$\pm$0.53, +0.08$\pm$0.65 and -0.10$\pm$0.65 points at 28, 50 and 88 M parameters, indistinguishable from zero at every capacity ($\pm$ is the across-seed standard deviation). That component is specific, not mechanical: random merges with the identical size profile yield only +0.68 points, and the three backbones agree to within 0.1 points. But it is overwhelmingly category coarsening, not alias correction: across the 37 merged groups, type coarsenings supply 94% of the gain and alias collapses only 7%. We also detect no interaction between consolidation and backbone size: tripling backbone parameters is worth +1.50$\pm$0.57 points on the raw catalog and +1.42$\pm$00.44 on the canonical one, a within-seed interaction of -0.08 [-0.79,+0.63]. On this archive, the reported consolidation gain primarily reflects the evaluation label space, and separating that out costs one evaluation

Comments: 9 pages, 4 figures, was accepted by a computer vision conference workshop

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)

Cite as: arXiv:2611.08655 [cs.CV]

(or arXiv:2611.08655v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.08655

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Xiang Ma [view email] [v1] Thu, 5 Nov 2026 20:01:20 UTC (307 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Scoring, Not Learning: Decomposing Catalog-Consolidation Gains in Web-Scraped Retail Product Recognition, by Kaden Leis and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs cs.AI

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • Consolidation gains of 4.0 points can be recovered by simple re-scoring without retraining.
  • Retraining on consolidated catalogs adds statistically insignificant improvements.
  • 94% of the gain comes from category coarsening, not alias correction.
  • No interaction exists between catalog consolidation and model size.

Highlights and analysis are generated automatically and may contain errors. Check the original source.