Semantic Scholar Open Access 2018 1302 sitasi

End-To-End Multi-Task Learning With Attention

Shikun Liu Edward Johns A. Davison

Abstrak

We propose a novel multi-task learning architecture, which allows learning of task-specific feature-level attention. Our design, the Multi-Task Attention Network (MTAN), consists of a single shared network containing a global feature pool, together with a soft-attention module for each task. These modules allow for learning of task-specific features from the global features, whilst simultaneously allowing for features to be shared across different tasks. The architecture can be trained end-to-end and can be built upon any feed-forward neural network, is simple to implement, and is parameter efficient. We evaluate our approach on a variety of datasets, across both image-to-image predictions and image classification tasks. We show that our architecture is state-of-the-art in multi-task learning compared to existing methods, and is also less sensitive to various weighting schemes in the multi-task loss function. Code is available at https://github.com/lorenmt/mtan.

Topik & Kata Kunci

Computer Science

Penulis (3)

Shikun Liu

Edward Johns

A. Davison

Format Sitasi

APA MLA BibTeX

Liu, S., Johns, E., Davison, A. (2018). End-To-End Multi-Task Learning With Attention. https://doi.org/10.1109/CVPR.2019.00197

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →

Lihat di Sumber doi.org/10.1109/CVPR.2019.00197

Informasi Jurnal

Tahun Terbit: 2018
Bahasa: en
Total Sitasi: 1302×
Sumber Database: Semantic Scholar
DOI: 10.1109/CVPR.2019.00197
Akses: Open Access ✓