Syllabus
-
EventDateTopicContents
-
Lecture02/19/2025 15:10
WednesdayCourse IntroductionLogistic, Introduction, History
-
Lecture02/26/2025 15:10
WednesdayClassic Vision IImage processing: image gradient, filter, convolution.
Classic edge/corner/line detection methods: Canny edge detection, Harris corner detection, line fitting.
-
Lecture03/05/2025 15:10
WednesdayClassic Vision II and Deep Learning IEdge/line detection: Canny edge detection, line fitting(RANSAC, Hough transform).
Corner detection and feature descriptors: Harris corner detection, feature.
Outline of deep leanring.
-
Lecture03/12/2025 15:10
WednesdayDeep Learning IIOutline of deep leanring.
Network structure: Multi-Layer Perceptron (MLP) and Convolutional Neural Network (CNN).
-
Assignment03/14/2025
FridayAssignment #1 released -
Lecture03/19/2025 15:10
WednesdayDeep Learning IIICNN Training: weight initialization, loss, optimizer (gradient descent, SGD, Adam), learning rate.
-
Lecture03/26/2025 15:10
WednesdayDeep Learning IVUnderfitting and overfitting: batch normalization, skip link, augmentation, regularization
Classification task: KNN, SoftMax, cross entropy loss
-
Due03/29/2025 23:59
SaturdayAssignment #1 due -
Lecture04/02/2025 15:10
WednesdayDeep Learning IVClassification task: receptive field, architecture(VGG, ResNet…)
Segmentation task: K-Means, upsampling, architecture (FCN, UNet)
-
Lecture04/09/2025 15:10
Wednesday3D Vision ICamera model: pinhole camera, lense, intrinsic, extrinsic, calibration
Depth image: sensor, stereo
-
Assignment04/11/2025
FridayAssignment #2 released -
Lecture04/16/2025 15:10
Wednesday3D Vision II (3D Deep Learning)3D data (voxel, mesh); 3D Deep Learning: Point, Mesh; 3D Deep Learning: Sparse Voxel Conv
-
Lecture04/23/2025 17:10
WednesdayTemporal Analysis IMotion and optical flow
-
Due04/26/2025 23:59
SaturdayAssignment #2 due -
Exam04/30/2025 15:10
WednesdayMidterm Exam (to be assigned) -
Lecture04/30/2025 15:10
WednesdayTemporal Analysis IIRNN, LSTM, GRU; Video Analysis: 3D CNN
-
Assignment05/02/2025
FridayAssignment #3 released -
Peking University Anniversary05/07/2025
WednesdayOne Week Break (Labor Day Holiday) -
Lecture05/14/2025 15:10
WednesdayGuest Lecture by Dr. Zhizheng ZhangAttention mechanism, transformer, visual transformer, vision language pretraining, large language model, vision language model.
-
Due05/17/2025 23:59
SaturdayAssignment #3 due -
Lecture05/21/2025 15:10
WednesdayObject Detection and Instance Segmentation2D Object detector (SSD, RCNN series, YOLO); Instance Segmentation, Panoptic Segmentation; 3D object detection and instance segmentation
-
Assignment05/24/2025
SaturdayAssignment #4 released -
Lecture05/28/2025 15:10
WednesdayGenerative ModelVAE, GAN, Diffusion, text-to-image generation.
-
Lecture06/04/2025 15:10
WednesdayEmbodied AIObject grasping, object manipulation, locomotion and navigation, embodied vision-language models.
-
Due06/07/2025 23:59
SaturdayAssignment #4 due -
Exam06/18/2025 13:59
WednesdayFinalterm Exam