A Multimodal, Multitask System for Generating E Commerce Text Listings from Images

TL;DR

This paper introduces a multi-task, hierarchical vision-to-text system for generating accurate e-commerce product descriptions from images, reducing factual errors and improving efficiency over existing models.

Contribution

It proposes a novel multi-task learning architecture with hierarchical generation, enhancing factual accuracy and reducing latency in image-to-text e-commerce listings.

Findings

Hierarchical generation reduces factual hallucinations by 44.5%.

Multi-task learning improves attribute classification by 6.6%.

Model is 3.5 times faster than comparable vision-to-language models.

Abstract

Manually generating catchy descriptions and names is labor intensive and a slow process for retailers. Although generative AI provides an automation solution in form of Vision to Language Models (VLM), the current VLMs are prone to factual "hallucinations". Siloed, single task models are not only inefficient but also fail to capture interdependent relationships between features. To address these challenges, we propose an end to end, multi task system that generates factually grounded textual listings from a single image. The contributions of this study are two proposals for the model architecture. First, application of multi task learning approach for fine tuning a vision encoder where a single vision backbone is jointly trained on attribute prediction such as color, hemline and neck style and price regression. Second, introduction of a hierarchical generation process where the model's own predicted attributes are embedded in a prompt and fed to the text decoder to improve factual consistency. The experiments demonstrate the superiority of this architecture. The multi tasking approach outperforms both the independent price regression, with a 3.6% better R2 Value and attribute classification, with a 6.6% improvement F1 score. Critically, the hierarchical generation process proves highly effective, slashing the factual hallucination rate from 12.7% to 7.1%, a 44.5% relative reduction, compared to a non hierarchical ablation. The hierarchical approach also reduces the latency of the autoregressive text generation process by a factor of 3.5 when compared to direct vision to language model of similar size. One minor caveat is that the model does perform 3.5% worse than direct vision-to-language model on ROUGE-L score.