딥러닝 기초

1.modality / multi-modal / VQA

post-thumbnail

2.pre-training / fine-tuning / transfer learning / prompt-tuning

post-thumbnail

3.BERT

post-thumbnail

4.stable diffusion

post-thumbnail

5.Atrous depth-wise separable convolution

post-thumbnail

6.reparameterized convolution

post-thumbnail

7.normalization layers

post-thumbnail

8.Atrous Convolution

post-thumbnail

9.Encoder/decoder 깊이의 영향

post-thumbnail

10.Cross-sample augmentation

post-thumbnail

11.Contrastive Learning

post-thumbnail

12.Similarity Contrastive Estimation(SCE)

post-thumbnail

13.Masked Modeling

post-thumbnail

14.Knowledge Distillation

post-thumbnail

15.MoCO: Momentum Contrast for Unsupervised Visual Representation Learning

post-thumbnail

16.Sharpness-Aware Minimization(SAM) / Weight Decay /

post-thumbnail

17.Adam Optimizer

post-thumbnail

18.Mixup Data Augmentation

post-thumbnail

19.[torch] cross entropy loss

post-thumbnail

20.Epoch, Batch Size, Iteration

post-thumbnail

21.Non Maximum Suppression (NMS) + Soft NMS

post-thumbnail

22.InfoNCE (Information Noise-Contrastive Estimation)

post-thumbnail

23.MAE (Masked Auto Encoding) are scalable Vision Learner

post-thumbnail

24.linear probing VS fine-tuning

post-thumbnail

25.Intermediate fine tuning

post-thumbnail

26.FLOPs(Floating Point Operations Per Second)

post-thumbnail

27.Optical Flow

post-thumbnail

28.Generative Pre-training / Language Modeling (LM) Loss / PrefixLM

post-thumbnail

29.이미지 도메인 task 정리

post-thumbnail

30.[CoCa] dual encoder for visual Foundation model

post-thumbnail

31.[CoCa] Encoder-Decoder for visual Foundation model

post-thumbnail

32.[CoCa] 용어 정리

post-thumbnail

33.casual masking transformer

post-thumbnail

34.linear probing VS fine-tuning

post-thumbnail

35.GFLOP

post-thumbnail

36.with torch.cuda.amp.autocast()

post-thumbnail

37.In-context learning

post-thumbnail

38.in context learning - 메모리 메커니즘

post-thumbnail