Schedule

Lectures are Mondays and Wednesdays, 4:30pm to 6pm. Attendance is not required. Recordings will be posted after each lecture in case you are unable the attend the scheduled time.

We will hold lectures remotely over Zoom for the first few weeks. See Canvas for the Zoom meeting information.

Some lectures have reading drawn from the course notes of Stanford CS 231n, written by Andrej Karpathy.

Some lectures have optional reading from the book Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville (GBC for short). The entire text of the book is available for free online so you don’t need to buy a copy.

Event	Date	Description	Course Materials
Lecture 1 [Remote]	Wednesday January 5	Course Introduction Computer vision overview Historical context Course logistics	[slides] [video (UMich only)] [FA2019 video (public)] [Python tutorial] [GBC Sec 1.2] [GBC Sec 6.6]
Lecture 2 [Remote]	Monday January 10	Image Classification Data-driven approach K-Nearest Neighbor Hyperparameters Cross-validation	[slides] [video (UMich only)] [FA2019 video (public)] [231n Image Classification]
Lecture 3 [Remote]	Wednesday January 12	Linear Classifiers Algebraic / Visual / Geometric viewpoints Softmax / SVM classifiers	[slides] [video (UMich only)] [FA2019 video (public)] [231n Linear Classification]
A1 Due	Friday January 14	Assignment 1 Due PyTorch warmup kNN Classifier	[Assignment 1]
	Monday January 17	No class MLK Day
Lecture 4 [Remote]	Wednesday January 19	Regularization + Optimization Regularization Weight decay Stochastic Gradient Descent Momentum, AdaGrad, Adam Second-order optimizers	[slides] [video (UMich only)] [FA2019 video (public)] [CS231n Optimization] [GBC Sec. 8.1 to 8.6]
Lecture 5 [Remote]	Monday January 24	Neural Networks Feature transforms Fully-connected networks Universal approximation Convexity	[slides] [video (UMich only)] [FA2019 video (public)] [231n Neural Networks] [GBC Sec. 6.1 to 6.4] [Nielsen on Universal Approximation]
Lecture 6 [Remote]	Wednesday January 26	Backpropagation Computational Graphs Backpropagation Matrix multiplication example	[slides] [video (UMich only)] [FA2019 video (public)] [Backprop for matrix multiply] [231n Backpropagation] [Olah on Backprop] [Nielsen on Backprop]
A2 Due	Friday January 28	Assignment 2 Due Linear classifiers Two-layer network	[Assignment 2]
Lecture 7 [Remote]	Monday January 31	Convolutional Networks Convolution Pooling Batch Normalization	[slides] [video (UMich only)] [FA2019 video (public)] [CS231n ConvNets] [GBC Chapter 9]
Lecture 8 [Remote]	Wednesday February 2	CNN Architectures I BatchNorm, AlexNet, VGG, ResNet Size vs Accuracy	[slides] [video (UMich only)] [FA2019 video (public)] [AlexNet] [VGG] [GoogLeNet] [ResNet] [ResNeXt]
Lecture 9 [Remote]	Monday February 7	Training Neural Networks I Activation functions Data preprocessing Weight initialization	[slides] [video (UMich only)] [FA2019 video (public)] [CS231n Training I]
Lecture 10 [Remote]	Wednesday February 9	Training Neural Networks II Data augmentation Regularization (Dropout, etc) Learning rate schedules Hyperparameter optimization Model ensembles	[slides] [video (UMich only)] [FA2019 video (public)] [CS231n Training II] [Karpathy "Recipe for Training"]
A3 Due	Friday February 11	Assignment 3 Due Modular API Convolutional Networks Batch Normalization Autograd	[Assignment 3]
Lecture 11 [Remote]	Monday February 14	CNN Architectures II Grouped and Separable Convolution ResNeXt Squeeze-and-Excite MobileNets / ShufleNets Neural Architecture Search EfficientNets NFNets Revisting ResNets RegNets	[slides] [video (UMich only)]
Lecture 12 [Remote]	Wednesday February 16	Deep Learning Software Dynamic vs Static graphs PyTorch, TensorFlow	[slides] [video (UMich only)] [FA2019 video (public)]
	Monday February 21	No class President's Day
Midterm	Wednesday February 23	Midterm Exam Details TBD
	Monday February 28	No class Spring break
	Wednesday March 3	No Class Spring break
Lecture 13 [Remote]	Monday March 7	Object Detection Transfer learning Object detection task R-CNN detector Non-Max Suppression (NMS) Mean Average Precision (mAP)	[slides] [video (UMich only)] [FA2019 video (public)] [R-CNN paper]
Lecture 14 [Remote]	Wednesday March 9	Object Detectors Single-stage vs two-stage detectors Region Proposal Networks (RPN), Anchor Boxes Two-Stage Detectors: Fast R-CNN, Faster R-CNN Feature Pyramid Networks	[slides] [video (UMich only)] [Girshick, Object Detection as a ML Problem] [Fast R-CNN paper] [Faster R-CNN paper] [RetinaNet paper] [FCOS paper]
Lecture 15 [Remote]	Monday March 14	Image Segmentation Single-Stage Detectors: RetinaNet, FCOS Semantic segmentation Instance segmentation Keypoint estimation	[slides] [video (UMich only)] [FA2019 video (public)]
Lecture 16 [Remote]	Wednesday March 16	Recurrent Networks RNN, LSTM, GRU Language modeling Sequence-to-sequence Image captioning	[slides] [video (UMich only)] [FA2019 video (public)] [Karpathy "Unreasonable Effectiveness"]
Lecture 17 [Remote]	Monday March 21	Attention Multimodal attention Self-Attention Transformers	[slides] [video (UMich only)] [FA2019 video (public)] [Bloem "Transformers from Scratch"] [Alammar "The Illustrated Transformer"]
Lecture 18 [Remote]	Wednesday March 23	Vision Transformers ViT, DeiT Swin, MViT DETR MLP-like architectures	[slides] [video (UMich only)]
Lecture 19 [Remote]	Monday March 28	Generative Models I Supervised vs Unsupervised learning Discriminative vs Generative models Autoregressive models Variational Autoencoders	[slides] [video (UMich only);] [FA2019 video (public)]
A4 due	Tuesday March 29	Assignment 4 Due Object detection	[Assignment 4]
Lecture 20 [Remote]	Wednesday March 30	Generative Models II More Variational Autoencoders Generative Adversarial Networks Normalizing Flows and Diffusion models (maybe)	[slides] [video (UMich only)] [FA2019 video (public)]
Lecture 21 [Remote]	Monday April 4	Visualizing Models and Generating Images Feature visualization Adversarial examples DeepDream, Style transfer	[slides] [video (UMich only)] [FA2019 video (public)] [Distill "Feature Visualization"] [Distill "Building Blocks of Interpretability"] [DeepDream] [neural-style]
Lecture 22 [Remote]	Wednesday April 6	Self-Supervised Learning Colorization, inpainting Contrastive learning Masked autoencoding Learning from language	[slides] [video (UMich only)]
Lecture 23 [Remote]	Monday April 11	3D vision 3D shape representations Depth estimation 3D shape prediction Voxels, Pointclouds, SDFs, Meshes Implicit functions, NeRF	[slides] [video (UMich only)] [FA2019 video (public)]
A5 Due	Tuesday April 12	Assignment 5 Due RNNs Image captioning Transformers	[Assignment 5]
Lecture 24 [Remote]	Wednesday April 13	Videos Video classification Early / Late fusion 3D CNNs Two-stream networks Transformer-based models	[slides] [video (UMich only)] [FA2019 video (public)]
Lecture 25 [Remote]	Monday April 18	Conclusion Course recap The future of computer vision	[slides] [video (UMich only)] [FA2019 video (public)]
Mini-project due	Monday April 25	Mini-Project TBA	[Mini-Project]
A6 due	Tuesday April 26	Assignment 6 Due Variational Autoencoders Generative Adversarial Networks Style Transfer Feature visualization	[Assignment 6]