Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture delves into the importance of ground truths in shaping new algorithms, focusing on the face detection and saliency detection domains. The instructor discusses the challenges and recent developments in statistical learning, emphasizing the critical role of benchmarked datasets. Through exercises and discussions, students explore the trajectory of ground truths supporting academic articles, analyzing their accessibility, construction, and implications. The session also covers the impact of biases in algorithm development and the need for diverse datasets. Practical examples and methodologies are presented to illustrate the process of utilizing ground truths in algorithmic research.
This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.
Watch on Mediaspace