Catalog Phrase Grounding (CPG): Grounding of Product Textual Attributes in Product Images for e-commerce Vision-Language Applications

TL;DR

This paper introduces Catalog Phrase Grounding (CPG), a model that links product textual attributes to specific image regions in e-commerce, improving product understanding and matching accuracy.

Contribution

The paper presents a novel self-supervised multimodal transformer model trained on large-scale synthesized data, integrating general and specialized knowledge for improved product image-text grounding.

Findings

Achieves 5% average recall improvement in product-brand matching

Outperforms logo detection and ResNet50 baselines

Effective in global e-commerce applications

Abstract

We present Catalog Phrase Grounding (CPG), a model that can associate product textual data (title, brands) into corresponding regions of product images (isolated product region, brand logo region) for e-commerce vision-language applications. We use a state-of-the-art modulated multimodal transformer encoder-decoder architecture unifying object detection and phrase-grounding. We train the model in self-supervised fashion with 2.3 million image-text pairs synthesized from an e-commerce site. The self-supervision data is annotated with high-confidence pseudo-labels generated with a combination of teacher models: a pre-trained general domain phrase grounding model (e.g. MDETR) and a specialized logo detection model. This allows CPG, as a student model, to benefit from transfer knowledge from these base models combining general-domain knowledge and specialized knowledge. Beyond immediate catalog phrase grounding tasks, we can benefit from CPG representations by incorporating them as ML features into downstream catalog applications that require deep semantic understanding of products. Our experiments on product-brand matching, a challenging e-commerce application, show that incorporating CPG representations into the existing production ensemble system leads to on average 5% recall improvement across all countries globally (with the largest lift of 11% in a single country) at fixed 95% precision, outperforming other alternatives including a logo detection teacher model and ResNet50.