Catalog consolidation mainly changes evaluation not recognition accuracy

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

Computer Vision and Pattern RecognitionArtificial Intelligence

Summary

Building product catalogs from web images is cheap but noisy, with many mislabeled or visually indistinguishable entries. The authors studied a large cheese image dataset and showed that combining similar product categories improves measured accuracy mostly because it changes what counts as correct, not by making the recognition model better. Retraining the model after merging categories does not significantly improve results. Most of the accuracy gain comes from grouping broad product types rather than fixing mislabeled duplicates.

What this means in practice

  • For ecommerce platform engineers: Design catalog cleaning tools that improve retail product recognition metrics by carefully merging categories instead of retraining models more often.
  • For retail data pipeline teams: Refine product label spaces using coarser categories to reduce noise impact on recognition accuracy without changing model architectures.

Tested on one dataset.

Authors

Kaden Leis, Xiang Ma

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