Object Localization#
Object detection is a core task in computer vision focused on both localizing and classifying objects within an image. In this project, you will start with a simplified setting: detecting whether an image contains a single object of a predefined category, and if so, predicting its bounding box. Next, you will extend this to images with multiple objects of the same category, requiring the model to detect and localize each instance. Finally, you will handle objects from multiple classes, completing the object detection pipeline. At each stage, you will assess how the increased complexity affects model design, training, and evaluation. This progression will give you hands-on experience with the challenges of building an object detection system.
Difficulty |
Suggested Tutorials |
---|---|
Medium |
Grading
The project will be graded based on the following criteria. Points for each activity are awarded based on quality and completeness (partial credit possible).
Activity |
Points (max) |
---|---|
Build and evaluate a model for single-class, single-object localization |
10 |
Extend the model to handle multiple objects per image |
5 |
Extend the model to handle multiple categories |
2 |
Presentation (clarity & demo) |
3 |
Total |
0-20 |