Princeton COS 529

Code for the CS 529: MAdvanced Computer Vision assignments and course project at Princeton University.

---

List of Assignments

1. Probabilistic Graphical Model Inference: Implementing efficient inference in Markov Random Fields
2. Zero-shot Recognition: Recognizing animals from the Animals with Attributes dataset
3. Bundle Adjustment: Implementing bundle adjustment algorithm
4. Visual Question Answering: Build and train a model that can answer questions based on image information in the VQA dataset

---

Project

Ensembling Large-scale Object Detectors:

• Developed algorithms for building YOLO model bagging and boosting ensembles
• Obtained an average precision of 87.5% on the Flickr-32 dataset using a generic logo detector system of two boosted YOLO models

---

Tech Stack

• Python 3
• PyTorch
• Hugging Face
• NumPy
• SciPy

---

Report

You can access the report for the course project here

Research Papers Referred

• Large scale open-set deep logo detection
• Cascade R-CNN: Delving into High Quality Object Detection
• Scalable Logo Recognition using Proxies
• Rapid object detection using a boosted cascade of simple features
• You Only Look Once: Unified, Real-Time Object Detection