Towards Generalization of Models on Streets Imagery: Methods and Applications
The domains relevant to urban planning have been disrupted by the proliferation of highly granular city data and the advancements in machine learning. However, machine learning models are susceptible to pitfalls constraining their deployment in many applications including domains related to urban...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2025
|
| Online Access: | https://hdl.handle.net/1721.1/158316 |
| _version_ | 1826195520406683648 |
|---|---|
| author | Alhasoun, Fahad |
| author2 | González, Marta C. |
| author_facet | González, Marta C. Alhasoun, Fahad |
| author_sort | Alhasoun, Fahad |
| collection | MIT |
| description | The domains relevant to urban planning have been disrupted by the proliferation of highly
granular city data and the advancements in machine learning. However, machine learning models are susceptible to pitfalls constraining their deployment in many applications
including domains related to urban settings. There is much to be addressed between the
methods and applications before we can realize all potentials of machine learning to improve urban life. In this thesis, we focus on the use of streets imagery and classification
problems. We start motivating the thesis with a case study where deep learning models
are trained to predict street contexts (i.e. residential, park, commercial...etc) from streets
imagery. We then shift gears and discuss a novel unsupervised domain adaptation method
to address the drop in accuracy when models are tested outside the domain of the training
data (i.e. a model trained on San Francisco and tested in Boston). We further our discussion with a proof of concept of a framework to develop more generalized models starting
with a prototype of a system of streets imagery collection, labeling, and ending with how
we approach generalization by breaking the problem into smaller prediction tasks to aid in
more understanding of the interworking of the models. |
| first_indexed | 2025-03-10T08:36:04Z |
| format | Thesis |
| id | mit-1721.1/158316 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2025-03-10T08:36:04Z |
| publishDate | 2025 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1583162025-03-05T15:27:04Z Towards Generalization of Models on Streets Imagery: Methods and Applications Alhasoun, Fahad González, Marta C. Williams, John R. Massachusetts Institute of Technology. Center for Computational Science and Engineering The domains relevant to urban planning have been disrupted by the proliferation of highly granular city data and the advancements in machine learning. However, machine learning models are susceptible to pitfalls constraining their deployment in many applications including domains related to urban settings. There is much to be addressed between the methods and applications before we can realize all potentials of machine learning to improve urban life. In this thesis, we focus on the use of streets imagery and classification problems. We start motivating the thesis with a case study where deep learning models are trained to predict street contexts (i.e. residential, park, commercial...etc) from streets imagery. We then shift gears and discuss a novel unsupervised domain adaptation method to address the drop in accuracy when models are tested outside the domain of the training data (i.e. a model trained on San Francisco and tested in Boston). We further our discussion with a proof of concept of a framework to develop more generalized models starting with a prototype of a system of streets imagery collection, labeling, and ending with how we approach generalization by breaking the problem into smaller prediction tasks to aid in more understanding of the interworking of the models. Ph.D. 2025-03-05T15:26:59Z 2025-03-05T15:26:59Z 2021-09 2025-03-04T16:15:59.344Z Thesis https://hdl.handle.net/1721.1/158316 In Copyright - Educational Use Permitted Copyright MIT http://rightsstatements.org/page/InC-EDU/1.0/ application/pdf application/pdf Massachusetts Institute of Technology |
| spellingShingle | Alhasoun, Fahad Towards Generalization of Models on Streets Imagery: Methods and Applications |
| title | Towards Generalization of Models on Streets Imagery: Methods and Applications |
| title_full | Towards Generalization of Models on Streets Imagery: Methods and Applications |
| title_fullStr | Towards Generalization of Models on Streets Imagery: Methods and Applications |
| title_full_unstemmed | Towards Generalization of Models on Streets Imagery: Methods and Applications |
| title_short | Towards Generalization of Models on Streets Imagery: Methods and Applications |
| title_sort | towards generalization of models on streets imagery methods and applications |
| url | https://hdl.handle.net/1721.1/158316 |
| work_keys_str_mv | AT alhasounfahad towardsgeneralizationofmodelsonstreetsimagerymethodsandapplications |