Compositional Learning of Image-Text Query for Image Retrieval

19 Jun 2020  ·  Muhammad Umer Anwaar, Egor Labintcev, Martin Kleinsteuber ·

In this paper, we investigate the problem of retrieving images from a database based on a multi-modal (image-text) query. Specifically, the query text prompts some modification in the query image and the task is to retrieve images with the desired modifications. For instance, a user of an E-Commerce platform is interested in buying a dress, which should look similar to her friend's dress, but the dress should be of white color with a ribbon sash. In this case, we would like the algorithm to retrieve some dresses with desired modifications in the query dress. We propose an autoencoder based model, ComposeAE, to learn the composition of image and text query for retrieving images. We adopt a deep metric learning approach and learn a metric that pushes composition of source image and text query closer to the target images. We also propose a rotational symmetry constraint on the optimization problem. Our approach is able to outperform the state-of-the-art method TIRG \cite{TIRG} on three benchmark datasets, namely: MIT-States, Fashion200k and Fashion IQ. In order to ensure fair comparison, we introduce strong baselines by enhancing TIRG method. To ensure reproducibility of the results, we publish our code here: \url{}.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Retrieval with Multi-Modal Query Fashion200k ComposeAE Recall@1 22.8 # 2
Recall@10 55.3 # 1
Recall@50 73.4 # 1
Image Retrieval with Multi-Modal Query FashionIQ ComposeAE Recall@10 11.8 # 1
Image Retrieval Fashion IQ ComposeAE (Recall@10+Recall@50)/2 20.6 # 17
Image Retrieval with Multi-Modal Query MIT-States ComposeAE Recall@1 13.9 # 1
Recall@5 35.5 # 1
Recall@10 47.9 # 1