T-VSE: Transformer-Based Visual Semantic Embedding

Transformer models have recently achieved impressive performance on NLP tasks, owing to new algorithms for self-supervised pre-training on very large text corpora. In contrast, recent literature suggests that simple average word models outperform more complicated language models, e.g., RNNs and Transformers, on cross-modal image/text search tasks on standard benchmarks, like MS COCO. In this paper, we show that dataset scale and training strategy are critical and demonstrate that transformer-based cross-modal embeddings outperform word average and RNN-based embeddings by a large margin, when trained on a large dataset of e-commerce product image-title pairs.