Training Vision Transformers for Image Retrieval
This work addresses image retrieval for computer vision applications, offering incremental improvements over convolution-based methods.
The authors tackled image retrieval by proposing a vision transformer model trained with a metric learning objective, achieving state-of-the-art results on category-level benchmarks like Stanford Online Product, In-Shop, and CUB-200, and competitive performance on particular object retrieval tasks such as ROxford and RParis.
Transformers have shown outstanding results for natural language understanding and, more recently, for image classification. We here extend this work and propose a transformer-based approach for image retrieval: we adopt vision transformers for generating image descriptors and train the resulting model with a metric learning objective, which combines a contrastive loss with a differential entropy regularizer. Our results show consistent and significant improvements of transformers over convolution-based approaches. In particular, our method outperforms the state of the art on several public benchmarks for category-level retrieval, namely Stanford Online Product, In-Shop and CUB-200. Furthermore, our experiments on ROxford and RParis also show that, in comparable settings, transformers are competitive for particular object retrieval, especially in the regime of short vector representations and low-resolution images.