MAGNeto: An Efficient Deep Learning Method for the Extractive Tags Summarization Problem

In this work, we study a new image annotation task named Extractive Tags Summarization (ETS). The goal is to extract important tags from the context lying in an image and its corresponding tags. We adjust some state-of-the-art deep learning models to utilize both visual and textual information. Our proposed solution consists of different widely used blocks like convolutional and self-attention layers, together with a novel idea of combining auxiliary loss functions and the gating mechanism to glue and elevate these fundamental components and form a unified architecture. Besides, we introduce a simple but effective data augmentation technique dedicated to alleviate the effect of outliers on the final results. Last but not least, we explore a self-supervised pre-training strategy to further boost the performance of the model by making use of the abundant amount of available unlabeled data. Our model shows the good results as 90% F-1 score on the public NUS-WIDE benchmark, and 50% F-1 score on a noisy large-scale real-world private dataset. Source code for reproducing the experiments is publicly available at: https://github.com/pixta-dev/labteam.