ABCDEFGHIJ
1
1
2
3
▶ Curriculum Section
4
Instructor: Jongmin Lee
5
6
FinishChap.Name of Chap.Clip.Name of Clip (Topic)Class indexMin.Sec.
7
Part 2. Computer Vision Specific Algorithms/Theory/Frameworks + Mini-Lab (45h)
8
01Preliminary01OverviewCh 1.Preliminary -1.Overview1418
9
01Preliminary02Linear algebra basic: vector and matrixCh 1.Preliminary -2.Linear algebra basic: vector and matrix3437
10
01Preliminary03Probability basic: random variable and Bayes'Ch 1.Preliminary -3.Probability basic: random variable and Bayes'1644
11
01Preliminary04Mini-Lab: OpenCV, Matplotlib Ch 1.Preliminary -4.Mini-Lab: OpenCV, Matplotlib 2512
12
01Preliminary05Mini-Lab: PIL, scikit-imageCh 1.Preliminary -5.Mini-Lab: PIL, scikit-image836
13
01Preliminary06Mini-Lab: PyTorch and Torchvision 1Ch 1.Preliminary -6.Mini-Lab: PyTorch and Torchvision 1173
14
01Preliminary07Mini-Lab: PyTorch and Torchvision 2Ch 1.Preliminary -7.Mini-Lab: PyTorch and Torchvision 21340
15
01Preliminary08Mini-Lab: Logging, WAN-DB Ch 1.Preliminary -8.Mini-Lab: Logging, WAN-DB 117
16
02Classical Computer Vision01OverviewCh 2.Classical Computer Vision -1.Overview158
17
02Classical Computer Vision02Local image featuresCh 2.Classical Computer Vision -2.Local image features836
18
02Classical Computer Vision03ConvolutionCh 2.Classical Computer Vision -3.Convolution84
19
02Classical Computer Vision04Edge and CornerCh 2.Classical Computer Vision -4.Edge and Corner1640
20
02Classical Computer Vision05Mini-Lab: Edge detectionCh 2.Classical Computer Vision -5.Mini-Lab: Edge detection659
21
02Classical Computer Vision06Mini-Lab: Harris corner detectionCh 2.Classical Computer Vision -6.Scale-invariant feature transform (SIFT)541
22
02Classical Computer Vision07BlobCh 2.Classical Computer Vision -7.Blob739
23
02Classical Computer Vision08Mini-Lab: Blob detection Ch 2.Classical Computer Vision -8.Mini-Lab: Blob detection 850
24
02Classical Computer Vision09Scale-invariant feature transform (SIFT)Ch 2.Classical Computer Vision -9.Model fitting and least square 2748
25
02Classical Computer Vision10Mini-Lab: SIFT Ch 2.Classical Computer Vision -10.Mini-Lab: SIFT 1348
26
02Classical Computer Vision11Mini-Lab: ORB Ch 2.Classical Computer Vision -11.Mini-Lab: ORB 556
27
02Classical Computer Vision12Model fitting and least square Ch 2.Classical Computer Vision -12.Mini-Lab: DEGENSAC1241
28
02Classical Computer Vision13RANSACCh 2.Classical Computer Vision -13.RANSAC1038
29
02Classical Computer Vision14Mini-Lab: RANSAC Ch 2.Classical Computer Vision -14.Mini-Lab: RANSAC 547
30
02Classical Computer Vision15Mini-Lab: DEGENSACCh 2.Classical Computer Vision -15.Fitting and matching513
31
02Classical Computer Vision16Hough transformCh 2.Classical Computer Vision -16.Hough transform952
32
02Classical Computer Vision17Mini-Lab: Hough transform Ch 2.Classical Computer Vision -17.Mini-Lab: Hough transform 524
33
02Classical Computer Vision18Fitting and matchingCh 2.Classical Computer Vision -18.Overview827
34
02Classical Computer Vision19Image representation with local featuresCh 2.Classical Computer Vision -19.Image representation with local features922
35
02Classical Computer Vision20Classification modelsCh 2.Classical Computer Vision -20.Classification models1522
36
03Deep Learning01OverviewCh 3.Deep Learning -1.Overview1014
37
03Deep Learning02Neural Network optimizationCh 3.Deep Learning -2.Neural Network optimization3058
38
03Deep Learning03CNNsCh 3.Deep Learning -3.CNNs1410
39
03Deep Learning04Overfitting and Network initializationCh 3.Deep Learning -4.Overfitting and Network initialization216
40
03Deep Learning05AlexNet, LeNet, VGGCh 3.Deep Learning -5.AlexNet, LeNet, VGG1257
41
03Deep Learning06Mini-Lab: AlexNetCh 3.Deep Learning -6.Mini-Lab: AlexNet1337
42
03Deep Learning07Mini-Lab: VGGCh 3.Deep Learning -7.Mini-Lab: VGG1035
43
03Deep Learning08Mini-Lab: Explainable CNNCh 3.Deep Learning -8.Mini-Lab: Explainable CNN1044
44
03Deep Learning09ResNetCh 3.Deep Learning -9.ResNet1552
45
03Deep Learning10Mini-Lab: ResNetCh 3.Deep Learning -10.Mini-Lab: ResNet644
46
03Deep Learning11Mini-Lab: Skip ConnectionCh 3.Deep Learning -11.Mini-Lab: Skip Connection650
47
03Deep Learning12Mini-Lab: Batch normalization and variationsCh 3.Deep Learning -12.Mini-Lab: Batch normalization and variations1232
48
03Deep Learning13Beyond ResNetCh 3.Deep Learning -13.Beyond ResNet1126
49
03Deep Learning14Mini-Lab: DenseNet, SENet Ch 3.Deep Learning -14.Mini-Lab: DenseNet, SENet 442
50
03Deep Learning15Mini-Lab: EfficientNetCh 3.Deep Learning -15.Mini-Lab: EfficientNet55
51
03Deep Learning16Introduction of Efficient CNNCh 3.Deep Learning -16.Introduction of Efficient CNN842
52
03Deep Learning17SqueezeNet, ShiftCh 3.Deep Learning -17.SqueezeNet, Shift1731
53
03Deep Learning18MobileNetV1, ShuffleNetCh 3.Deep Learning -18.MobileNetV1, ShuffleNet269
54
03Deep Learning19Mini-Lab: SqueezeNet, ShuffleNetV2 Ch 3.Deep Learning -19.Mini-Lab: SqueezeNet, ShuffleNetV2 1120
55
03Deep Learning20Mini-Lab: MobileNetV2, MobileNetV3Ch 3.Deep Learning -20.Mini-Lab: MobileNetV2, MobileNetV31232
56
03Deep Learning21Vision Transformer 1: Attention MechanismsCh 3.Deep Learning -21.Vision Transformer 1: Attention Mechanisms2416
57
03Deep Learning22Vision Transformer 2: TransformerCh 3.Deep Learning -22.Vision Transformer 2: Transformer1452
58
03Deep Learning23Vision Transformer 3: ViTCh 3.Deep Learning -23.Vision Transformer 3: ViT1553
59
03Deep Learning24Mini-Lab: Multi-head AttentionCh 3.Deep Learning -24.Mini-Lab: Multi-head Attention107
60
03Deep Learning25Mini-Lab: Vision TransformerCh 3.Deep Learning -25.Mini-Lab: Vision Transformer938
61
03Deep Learning27Swin Transformer: Hierarchical TransformerCh 3.Deep Learning -27.Swin Transformer: Hierarchical Transformer2437
62
03Deep Learning28Swin Transformer V2Ch 3.Deep Learning -28.Swin Transformer V21123
63
03Deep Learning29MLP-Mixer, ConViTCh 3.Deep Learning -29.MLP-Mixer, ConViT
64
03Deep Learning31Special Issue: Steerable CNNs and EquivarianceCh 3.Deep Learning -31.Special Issue: Steerable CNNs and Equivariance
65
03Deep Learning32Special Issue: Neural Arcitecture SearchCh 3.Deep Learning -32.Special Issue: Neural Arcitecture Search
66
04Representation learning01OverviewCh 4.Representation learning -1.Overview160
67
04Representation learning02Metric learning 1: Similarity and DistanceCh 4.Representation learning -2.Metric learning 1: Similarity and Distance1422
68
04Representation learning03Metric learning 2: Classical Metric LearningCh 4.Representation learning -3.Metric learning 2: Classical Metric Learning139
69
04Representation learning04
Metric learning 3: Deep Metric Learning (Siamese networks and triplet loss)
Ch 4.Representation learning -4.Metric learning 3: Deep Metric Learning (Siamese networks and triplet loss)
1532
70
04Representation learning05Metric learning 4: Sampling MattersCh 4.Representation learning -5.Metric learning 4: Sampling Matters842
71
04Representation learning06Metric learning 5: Quadruplet NetworksCh 4.Representation learning -6.Metric learning 5: Quadruplet Networks759
72
04Representation learning07Metric learning 6: Visual ApplicationsCh 4.Representation learning -7.Metric learning 6: Visual Applications2556
73
04Representation learning08Face Recogntion: FaceNetCh 4.Representation learning -8.Face Recogntion: FaceNet161
74
04Representation learning09Image Retrieval: Fine-Grained ClassificationCh 4.Representation learning -9.Image Retrieval: Fine-Grained Classification228
75
04Representation learning10Visual Place Recognition: NetVLADCh 4.Representation learning -10.Visual Place Recognition: NetVLAD2721
76
04Representation learning11Landmark Recognition: DELFCh 4.Representation learning -11.Landmark Recognition: DELF234
77
04Representation learning12Average Precision Loss (AP Loss)Ch 4.Representation learning -12.Average Precision Loss (AP Loss)2546
78
04Representation learning13Image clustering 1: K-meansCh 4.Representation learning -13.Image clustering 1: K-means1610
79
04Representation learning14Image clustering 2: Unsupervised Metric LearningCh 4.Representation learning -14.Image clustering 2: Unsupervised Metric Learning2136
80
04Representation learning15Image clustering 3: t-SNECh 4.Representation learning -15.Image clustering 3: t-SNE1254
81
04Representation learning16Data Augmentation 1: Rule-based ApproachCh 4.Representation learning -16.Data Augmentation 1: Rule-based Approach3238
82
04Representation learning17Data Augmentation 2: GAN-based ApproachCh 4.Representation learning -17.Data Augmentation 2: GAN-based Approach3623
83
04Representation learning18Data Augmentation 3: AutoML-based ApproachCh 4.Representation learning -18.Data Augmentation 3: AutoML-based Approach3641
84
04Representation learning19Self-supervised learning (SSL): OverviewCh 4.Representation learning -19.Self-supervised learning (SSL): Overview1359
85
04Representation learning20SSL - Proxy tasks 1: exemplarCh 4.Representation learning -20.SSL - Proxy tasks 1: exemplar1329
86
04Representation learning21SSL - Proxy tasks 2: context prediction, jigsaw puzzlesCh 4.Representation learning -21.SSL - Proxy tasks 2: context prediction, jigsaw puzzles146
87
04Representation learning22SSL - Proxy tasks 3: counting, multi-tasksCh 4.Representation learning -22.SSL - Proxy tasks 3: counting, multi-tasks1111
88
04Representation learning23SSL - Proxy tasks 4: rotation predictionCh 4.Representation learning -23.SSL - Proxy tasks 4: rotation prediction1430
89
04Representation learning24SSL - Contrastive Learning 1: NPID, MoCoCh 4.Representation learning -24.SSL - Contrastive Learning 1: NPID, MoCo2752
90
04Representation learning25SSL - Contrastive Learning 2: SimCLR, MoCov2Ch 4.Representation learning -25.SSL - Contrastive Learning 2: SimCLR, MoCov22410
91
04Representation learning26SSL - SimCLRv2, MaskFeatCh 4.Representation learning -26.SSL - SimCLRv2, MaskFeat1927
92
04Representation learning27SSL - BYOL, DINOCh 4.Representation learning -27.SSL - BYOL, DINO2525
93
04Representation learning28Semi-Supervised Learning 1: OverviewCh 4.Representation learning -28.Semi-Supervised Learning 1: Overview729
94
04Representation learning29
Semi-Supervised Learning 2: Entropy Minimization, Consistency Regularizaiton
Ch 4.Representation learning -29.Semi-Supervised Learning 2: Entropy Minimization, Consistency Regularizaiton
2647
95
04Representation learning30
Semi-Supervised Learning 3: Holistic Methods (MixMatch, ReMixMatch, FixMatch)
Ch 4.Representation learning -30.Semi-Supervised Learning 3: Holistic Methods (MixMatch, ReMixMatch, FixMatch)
2052
96
04Representation learning31Few-Shot LearningCh 4.Representation learning -31.Few-Shot Learning1736
97
04Representation learning32Meta-LearningCh 4.Representation learning -32.Meta-Learning931
98
04Representation learning33Few-Shot Learning Wrap-UpCh 4.Representation learning -33.Few-Shot Learning Wrap-Up345
99
04Representation learning34Knowledge Distillation 1: OverviewCh 4.Representation learning -34.Knowledge Distillation 1: Overview1322
100
04Representation learning35Knowledge Distillation 2: Relational Knowledge DistillationCh 4.Representation learning -35.Knowledge Distillation 2: Relational Knowledge Distillation825