"Using Eye-Gaze to Evaluate Neural Attention" by Shahansha Salim

Date of Submission

6-12-2020

Date of Award

12-12-2020

Institute Name (Publisher)

Indian Statistical Institute

Document Type

Master's Dissertation

Degree Name

Master of Technology

Subject Name

Computer Science

Department

Computer Vision and Pattern Recognition Unit (CVPR-Kolkata)

Supervisor

Garain, Utpal (CVPRU-ISI)

Abstract (Summary of the Work)

The ability to selectively concentrate on areas of interest while ignoring the rest is termed as attention in human beings. This ability has played a key role in survival as well as information processing. Neural Attention is said to be an effort to bring similar action of selectively concentrating areas of relevance in deep neural networks. This simple yet powerful concept has attracted a lot of research in recent years, yielding breakthrough results in Natural Language Processing (NLP) problems and main stream Computer Vision problems such as Image Caption Generation, Neural Machine Translation (NMT), Visual Question Answering (VQA), Action Recognition, Image Segmentation, etc. Only few works has been there articulating the relation between human attention and machine attention. Some recent efforts suggest that automatically learned attention maps can capture informative parts of an input signal and highlight human sensible regions of interest. Also, as the neural attention gets better, so is the performance of the network. However, there are no formal way of bench marking how good the learned attention is in a network. This seems necessary since visualizing attention as a means for logical correctness of the network is common. Since eye-gaze can better capture human visual reasoning, With this work, we are investigating how well neural attention compares with the visual grounding given by human cognitive modality on VQA tasks.

Comments

Master's dissertation submitted in 2020 (Roll No: CS1803)

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Share

COinS