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

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

9 Nov 2020arXiv:2011.04349archive 2025-07-28

Hieu Trong Phung, Anh Tuan Vu, Tung Dinh Nguyen, Lam Thanh Do, Giang Nam Ngo, Trung Thanh Tran, Ngoc C. Lê

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 loss function that aims to reduce the imbalance of the training data and a simple but effective data augmentation technique dedicated to alleviates the effect of outliers on the final results. Last but not least, we explore an unsupervised 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% F₁ score on the public NUS-WIDE benchmark, and 50% F₁ 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

Paper PDF Conference PDF Code

Code

pixta-dev/labteam officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data Augmentation Extractive Tags Summarization Self-Supervised Learning Unsupervised Pre-training

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position Encodings Attention Convolution Dense Connections Dropout Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection SGD with Momentum Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections