Understanding what a captioning network doesn't know
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2019
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/1721.1/122996 |
| _version_ | 1826200751081259008 |
|---|---|
| author | Yip, Richard B.,M. Eng.Massachusetts Institute of Technology. |
| author2 | Antonio Torralba. |
| author_facet | Antonio Torralba. Yip, Richard B.,M. Eng.Massachusetts Institute of Technology. |
| author_sort | Yip, Richard B.,M. Eng.Massachusetts Institute of Technology. |
| collection | MIT |
| description | This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. |
| first_indexed | 2024-09-23T11:40:52Z |
| format | Thesis |
| id | mit-1721.1/122996 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T11:40:52Z |
| publishDate | 2019 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1229962019-11-22T03:22:56Z Understanding what a captioning network doesn't know Yip, Richard B.,M. Eng.Massachusetts Institute of Technology. Antonio Torralba. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Electrical Engineering and Computer Science. This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (page 29). While recent years have seen significant advances in the capabilities of image recognition and classification neural networks, we still know little about the relationship between the activation of hidden layers and human-understandable concepts. Recent work in network interpretability has provided a framework for analyzing hidden nodes and layers, showing that in many convolutional architectures, there exists a significant correlation between groups of nodes and human-understandable concepts. We use this framework to investigate the encoding of images produced by standard image classification networks. We do this in the context of encoder-decoder image classification networks. These provide a natural way to observe the effect that perturbing node activations has on the image encoding by observing the generated captions, which are inherently understandable by humans and thus convenient and informative to use. We also generate and analyze captions of images modified by inserting small sub-images of single, human-interpretable concepts. These modifications and the resulting captions show the existence of training-triggered correlations between semantically dissimilar words. by Richard B. Yip. M. Eng. M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 2019-11-22T00:00:51Z 2019-11-22T00:00:51Z 2019 2019 Thesis https://hdl.handle.net/1721.1/122996 1127292891 eng MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 29 pages application/pdf Massachusetts Institute of Technology |
| spellingShingle | Electrical Engineering and Computer Science. Yip, Richard B.,M. Eng.Massachusetts Institute of Technology. Understanding what a captioning network doesn't know |
| title | Understanding what a captioning network doesn't know |
| title_full | Understanding what a captioning network doesn't know |
| title_fullStr | Understanding what a captioning network doesn't know |
| title_full_unstemmed | Understanding what a captioning network doesn't know |
| title_short | Understanding what a captioning network doesn't know |
| title_sort | understanding what a captioning network doesn t know |
| topic | Electrical Engineering and Computer Science. |
| url | https://hdl.handle.net/1721.1/122996 |
| work_keys_str_mv | AT yiprichardbmengmassachusettsinstituteoftechnology understandingwhatacaptioningnetworkdoesntknow |