Large Scale Long-tailed Product Recognition System at Alibaba
This paper tackles the challenge of long-tailed product recognition for large-scale e-commerce platforms like Alibaba, where imbalanced training data is prevalent. It is an incremental improvement by integrating side information into existing long-tail problem solutions.
The paper addresses the long-tailed product recognition problem in e-commerce by introducing a novel co-training system (SICoT) that leverages image-related side information. This system effectively transfers knowledge from head to tail classes, demonstrating scalable effectiveness across datasets with up to one million classes and achieving a significant gain in unique visitor conversion rate on Alibaba's visual search platform.
A practical large scale product recognition system suffers from the phenomenon of long-tailed imbalanced training data under the E-commercial circumstance at Alibaba. Besides product images at Alibaba, plenty of image related side information (e.g. title, tags) reveal rich semantic information about images. Prior works mainly focus on addressing the long tail problem in visual perspective only, but lack of consideration of leveraging the side information. In this paper, we present a novel side information based large scale visual recognition co-training~(SICoT) system to deal with the long tail problem by leveraging the image related side information. In the proposed co-training system, we firstly introduce a bilinear word attention module aiming to construct a semantic embedding over the noisy side information. A visual feature and semantic embedding co-training scheme is then designed to transfer knowledge from classes with abundant training data (head classes) to classes with few training data (tail classes) in an end-to-end fashion. Extensive experiments on four challenging large scale datasets, whose numbers of classes range from one thousand to one million, demonstrate the scalable effectiveness of the proposed SICoT system in alleviating the long tail problem. In the visual search platform Pailitao\footnote{http://www.pailitao.com} at Alibaba, we settle a practical large scale product recognition application driven by the proposed SICoT system, and achieve a significant gain of unique visitor~(UV) conversion rate.