
2021 Fall: Intelligent Image Recognition (지능형영상인식)
Lecture Notes
-
Due to COVID-19, we will continue online lectures with pre-recorded video lectures for some time.
For each chapter, please download PPT(Lecture Video), and play it in slideshow mode. -
Starting from Lecture 1, after watching each lecture video, each student needs to submit
a lecture summary via Google Classroom. Check your email to find the Google Classroom
link of CBNU/Intelligent Image Recognition.
-
Lecture0: Course Introduction [PPT (Lecture Video)]
-
Lecture1: Introduction To Image Recognition [PPT (Lecture Video)]
-
Lecture2: Image Classification [PPT (Lecture Video)]
-
Lecture3: Convolutional Neural Network [PPT (Lecture Video)]
-
Lecture4: Training with Backpropagation [PPT (Lecture Video)]
-
Lecture5: CNN Architectures [PPT (Lecture Video)]
-
Lecture6: Segmentation and Detection [PPT (Lecture Video)]
-
Lecture7: Fast Detection CNNs [PPT (Lecture Video)]
-
Lecture8: Generative Models [PPT (Lecture Video)]
-
Lecture9: Generative Adversarial Networks [PPT (Lecture Video)]
-
Final Exam: December 6th (Monday) 7PM~9PM, Location: E8-7 Room 307,
Open Note (Only Lecture Notes are allowed during the exam) -
Term Project: Presentation on December 13th (Monday) 7PM~9PM, E10 Room 406
-
All students who are studying deep learning must select Option (1).
Students whose major is not deep learning can select Option (2) with the professor's approval. -
(1) Train a CNN model of your choice using a public dataset or your own dataset. Demonstrate the inference and accuracy (You can choose the same CNN as your research topic)
-
(2) Paper Survey on CNNs or GANs for classification, detection, segmentation, augmentation, and present the summary of your survey result.
-
-
Overall Evaluation Results [Evaluation Scores]
-
If you have any questions regarding your scores, please send me an inquiry email.
-