Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Crack detection
The main focus of this project is to investigate how to combine few shot learning and domain adaptation techniques to utilize the information from ‘normal’ images and adapting the deep learning model to detect cracks/anomalies in varying environments.
Keywords: Master thesis, AI, artificial intelligence, industry collaboration, research project, few-shot learning, domain adaptation
Deep learning applications have been thriving over the last decade in many different domains, including computer vision and natural language understanding. The drivers for the vibrant development of deep learning have been the availability of abundant data, breakthroughs of algorithms and the advancements in hardware. The majority of models created today require a human to manually label data in a way that allows the model to learn how to make correct decisions. The collected datasets typically need to be on the one hand representative of all the different operating and environmental conditions and on the other hand of all the different classes. This is not feasible in practical applications. For rare events, such as for example faults, the dataset cannot be representative of the all the different fault types. Also collecting data under in all possibly environments can be both costly and can take long to collect (particularly in case of rare events). For datasets experiencing a domain shift, e.g. due to different environmental conditions, Domain adaptation (DA) can perform a knowledge transfer from a label-rich source domain to an unlabeled target domain. However, there have been several limitations to DA approaches, particularly for cases with rare events and with respect to their ability for online learning in new environments.
There are two paradigms in resolving the generalization issue for DA: robustness and adaptation. In this project, we explore how to build an adaptive deep learning model that can learn to detect rare events / anomalies from images acquired in a different domain.
Deep learning applications have been thriving over the last decade in many different domains, including computer vision and natural language understanding. The drivers for the vibrant development of deep learning have been the availability of abundant data, breakthroughs of algorithms and the advancements in hardware. The majority of models created today require a human to manually label data in a way that allows the model to learn how to make correct decisions. The collected datasets typically need to be on the one hand representative of all the different operating and environmental conditions and on the other hand of all the different classes. This is not feasible in practical applications. For rare events, such as for example faults, the dataset cannot be representative of the all the different fault types. Also collecting data under in all possibly environments can be both costly and can take long to collect (particularly in case of rare events). For datasets experiencing a domain shift, e.g. due to different environmental conditions, Domain adaptation (DA) can perform a knowledge transfer from a label-rich source domain to an unlabeled target domain. However, there have been several limitations to DA approaches, particularly for cases with rare events and with respect to their ability for online learning in new environments.
There are two paradigms in resolving the generalization issue for DA: robustness and adaptation. In this project, we explore how to build an adaptive deep learning model that can learn to detect rare events / anomalies from images acquired in a different domain.
1. Familiarize with Computer vision and domain adaptation literature
2. Literature review of state-of-the-art methods for anomaly detection, few shot learning and Domain adaptation/generalization
3. Propose an algorithm combining DA and few shot learning for anomaly detection.
4. Design a set of experiments to evaluate different domain adaptation approaches
5. Train and evaluate the approaches on various Industrial datasets
6. Real word application with our Industrial partner.
1. Familiarize with Computer vision and domain adaptation literature
2. Literature review of state-of-the-art methods for anomaly detection, few shot learning and Domain adaptation/generalization
3. Propose an algorithm combining DA and few shot learning for anomaly detection.
4. Design a set of experiments to evaluate different domain adaptation approaches
5. Train and evaluate the approaches on various Industrial datasets
6. Real word application with our Industrial partner.
**Professor**
Fisher Yu, http://yf.io and Olga Fink https://ims.ibi.ethz.ch/
**To apply**
Send a CV and master transcripts and project of interest to our PhD student inejjar@ethz.ch .We will usually reply within 2 days if there is a project to match.
**Professor** Fisher Yu, http://yf.io and Olga Fink https://ims.ibi.ethz.ch/
**To apply**
Send a CV and master transcripts and project of interest to our PhD student inejjar@ethz.ch .We will usually reply within 2 days if there is a project to match.