What Matters for Grocery Product Retrieval with Open Source Vision Language Models

arXiv:2605.18029v1 Announce Type: new Abstract: Multimodal product retrieval (MPR) underpins checkout-free retail and automated inventory systems, yet it demands fine-grained SKU discrimination that standard vision-language benchmarks fail to capture. We present the first systematic zero-shot evaluation of 190 open-source VLMs on the MPR task of the GroceryVision Challenge, isolating pre-training data, architecture, and input resolution. Our analysis yields three actionable findings. extbf{(1) Data quality trumps scale.} Switching from raw web-scrapes to filtered datasets delivers up to 16.6% accuracy gains, exceeding the benefit of doubling model parameters. extbf{(2) Efficient models can win.} MobileCLIP-B (150M parameters) outperforms 351M counterparts trained on noisy data. We introduce extit{semantic power density} (phi), an efficiency metric that penalizes sub-threshold accuracy. extbf{(3) A precision gap persists.} State-of-the-art models achieve 94.5% Recall@5 but suffer a 17.5% drop at Recall@1, revealing that contrastive embeddings cluster categories effectively but fail to rank visually similar SKUs. Code and evaluation scripts are available at rl{https://github.com/upeee/openmpr}.

Source: arXiv cs.CV | 2026-05-19