Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations
This work addresses the need for efficient and effective multi-task visual representations in industry applications like visual shopping, though it is incremental as it adapts existing methods to large-scale production systems.
The paper tackled the problem of scaling visual representation pretraining for a production visual discovery product by generating a billion-image dataset with weak supervision and using Vision Transformers, resulting in a 36% improvement in top-1 relevance and 23% improvement in click-through volume.
Large-scale pretraining of visual representations has led to state-of-the-art performance on a range of benchmark computer vision tasks, yet the benefits of these techniques at extreme scale in complex production systems has been relatively unexplored. We consider the case of a popular visual discovery product, where these representations are trained with multi-task learning, from use-case specific visual understanding (e.g. skin tone classification) to general representation learning for all visual content (e.g. embeddings for retrieval). In this work, we describe how we (1) generate a dataset with over a billion images via large weakly-supervised pretraining to improve the performance of these visual representations, and (2) leverage Transformers to replace the traditional convolutional backbone, with insights into both system and performance improvements, especially at 1B+ image scale. To support this backbone model, we detail a systematic approach to deriving weakly-supervised image annotations from heterogenous text signals, demonstrating the benefits of clustering techniques to handle the long-tail distribution of image labels. Through a comprehensive study of offline and online evaluation, we show that large-scale Transformer-based pretraining provides significant benefits to industry computer vision applications. The model is deployed in a production visual shopping system, with 36% improvement in top-1 relevance and 23% improvement in click-through volume. We conduct extensive experiments to better understand the empirical relationships between Transformer-based architectures, dataset scale, and the performance of production vision systems.