Self supervision for attention networks

Badri N. Patro, S. Kasturi G, Ansh Jain, Vinay P. Namboodiri

Research output: Chapter or section in a book/report/conference proceedingChapter in a published conference proceeding

3 Citations (SciVal)


In recent years, the attention mechanism has become a fairly popular concept and has proven to be successful in many machine learning applications. However, deep learning models do not employ supervision for these attention mechanisms which can improve the model's performance significantly. Therefore, in this paper, we tackle this limitation and propose a novel method to improve the attention mechanism by inducing "self-supervision". We devise a technique to generate desirable attention maps for any model that utilizes an attention module. This is achieved by examining the model's output for different regions sampled from the input and obtaining the attention probability distributions that enhance the proficiency of the model. The attention distributions thus obtained are used for supervision. We rely on the fact, that attenuation of the unimportant parts, allows a model to attend to more salient regions, thus strengthening the prediction accuracy. The quantitative and qualitative results published in this paper show that this method successfully improves the attention mechanism as well as the model's accuracy. In addition to the task of Visual Question Answering(VQA), we also show results on the task of Image classification and Text classification to prove that our method can be generalized to any vision and language model that uses an attention module.

Original languageEnglish
Title of host publication2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
Place of PublicationU. S. A.
Number of pages10
ISBN (Electronic)9780738142661
ISBN (Print)9781665446402
Publication statusPublished - 14 Jun 2021
Event2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021 - Virtual, Online, USA United States
Duration: 5 Jan 20219 Jan 2021

Publication series

NameProceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021
ISSN (Print)2472-6737
ISSN (Electronic)2642-9381


Conference2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021
Country/TerritoryUSA United States
CityVirtual, Online

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications


Dive into the research topics of 'Self supervision for attention networks'. Together they form a unique fingerprint.

Cite this