MetaUAS; Universal Anomaly Segmentation with One-Prompt Meta-Learning
NeurIPS 2024
Computer Vision
NExT-GPT; Any-to-Any Multimodal LLM
ICML 2024 Oral
Mixture-of-Experts with Expert Choice Routing
NeurIPS 2022
KAN; Kolmogorov–Arnold Networks
arxiv 2024
ImageBind; One Embedding Space To Bind Them All
CVPR 2023 Highlighted Paper
An Inverse Scaling Law for CLIP Training
NeurIPS 2023
HydraLoRA; An Asymmetric LoRA Architecture for Efficient Fine-Tuning
NeurIPS 2024 Oral
NV-Embed; Improved Techniques for Training LLMs as Generalist Embedding Models
ICLR 2025 under review, arxiv 2024
Fine-Grained Abnormality Prompt Learning for Zero-shot Anomaly Detection
ICLR 2025 under review, arxiv 2024
Vision Transformers Need Registers
ICLR 2024 Oral
GPU 설명
feat ChatGPT
Titans; Learning to Memorize at Test Time
arxiv 2024
VQ-VAE
Neural Discrete Representation Learning (NeurIPS 2017)
Masked Diffusion Models are Fast Distribution Learners
ICLR 2024 (?)
Consistency Models
arxiv 2023
All About Score-based Models
All About Score-based Models
All About Diffusion
All About Diffusion Models
Siamese Masked Autoencoders
NeurIPS 2023
MAE-AST; Masked Autoencoding Audio Spectogram Transformer
Interspeech 2022
Score-based Generative Modeling by Diffusion Process
Score-based Generative Modeling by Diffusion Process
(발표 자료) Beit; Bert pre-training of image transformers
(발표 자료) SSL with TS data
(발표 자료) MIM, CL
(발표 자료) MIM, CL
(paper) CAN; A Simple, Efficient and Scalable CMAE framework for learning Visual Representations
2023
(발표 자료) SwAV, DeepDPM
연세대학교 기초연구실 발표자료
Context Understanding - Visual Transformer
ViT, VT, DeiT, ConViT, CeiT, Swin Transformer, T2T-ViT, PVT
(CV-project) 08.Image Feature Analysis
ORL face dataset, Feature Visualization, Tensorboard
(CV-project) 07.Few Shot Learning
ORL face dataset, Siamese Network, Contrastive Loss Function, Face Recognition
(CV-project) 05.Advanced Object Detection
One-Stage Detection, YOLO v1, Real-Time Processing, NMS
(CV-project) 04.Object Detection
Two-Stage Detection, Faster-RCNN, Confidence Threshold, NMS
(CV-project) 03.Transfer Learning
VGG16, U-Net, Covid chest-xray
(paper 48) VICReg
2022
(CV-project) 02.Semantic Segmentation
U-Net, Covid chest-xray, Dice Similarity Coefficient
(paper 47) DINO
2021
(CV-project) 01.Image Classification
VGG19, Covid chest-xray, Top-N Accuracy
Transformer for OD and HOI
DETR, InteractNet, iCAN, UnionDet, HOTR
(paper 45) CAE
2022
(paper 44) SimMIM
2022
(CV summary) 24. Semantic Segmentation - FCN, DeepLab, DeconvNet, UNet
FCN, DeepLab, DeconvNet, UNet
(paper 43) BEIT
2022
(CV summary) 23. Deformable DeTR
Deformable DETR
(paper 42) MSN
2022
(CV summary) 21. Additional Object Detection Techniques
FPN, PANet, EfficientDet
(paper 40) GraphCL
2021
(CV summary) 20. Object Detection - YOLO
YOLO, One-stage Detector
(paper 39) AugSelf
2021
(paper 38) i-Mix
2021
(CV summary) 18. Object Detection - RCNN/Fast RCNN/Faster-RCNN
RCNN, Fast RCNN, Faster-RCNN
(CV summary) 17. Data Augmentation (3) - AutoML based
AutoML based Data Augmentation
(CV summary) 16. Data Augmentation (2) - GAN based
GAN based Data Augmentation
(paper 35) Mitigating Embedding and Class Assignment Mismatch in Unsupervised Image Classification
2020
(CV summary) 15. Data Augmentation (1) - Rule based
Rule based Data Augmentation
(paper 34) SCAN
2020
(CV summary) 14. Image Clustering
Image Clustering
(CV summary) 12. Representation Learning (3)
NetVLAD (2016), DELF (Deep Local Features) (2017)
(CV summary) 11. Representation Learning (2)
faceNet (2015), Image Retrieval, Beyond Binary Supervision (2019), Proxy Anchor Loss (2020)
(CV summary) 10. Representation Learning (1)
Metric Learning, Deep Metric Learning, Siamese Network, Quadruplet Network
(CV summary) 09. Vision Transformer (ViT)
Vision Transformer (ViT)
(CV summary) 08. MobileNet & ShuffleNet
MobileNet, ShuffleNet
(CV summary) 07. EfficientNet & SqueezeNet & Shift
EfficientNet, SqueezeNet, Shift
(CV summary) 06. ResNet & DenseNet & SENet
ResNet, DenseNet, SENet
(CV summary) 05. Explainable CNN
Explainable CNN
(paper 24) Selfie
2019
(CV summary) 04. LeNet & AlexNet & VGG
LeNet, AlexNet, VGG
(paper 23) S4L
2019
(paper 21) BigBiGAN
2019
(CV summary) 01. OpenCV
OpenCV in python
(paper 20) AMDIM
2019
(발표 자료) SimCLR, MoCo v1&v2
연세대학교 기초연구실 발표자료
(paper 9) SwAV
2021
(paper 8) DeepDPM
2022
(paper 6) CSI
2020
(paper 5) SimSiam
2020
(paper 4) BYOL
2020
(paper 3) MoCo v2
2020
(paper 2) MoCo v1
2020
(paper 1) SimCLR
2020
Deep Lab v3 +
Image Segmentation, Deep Lab v3
Mask R-CNN
Image Segmentation, Mask R-CNN
U-net
Image Segmentation, U-net
ConDeconvolutional Network
Image Segmentation, Deconvolutional Network
FCN (Fully Convolution Network for Semantic Segmentation)
Image Segmentation, FCN
Image Segmentation이란
Image Segmentation
SSD (Single Shot MultiBox Detector)
Object Detection, YOLO v2 & YOLO 9000
YOLO v2 & YOLO 9000
Object Detection, YOLO v2 & YOLO 9000
YOLO v1
Object Detection, YOLO, You Only Look Once
Fast,Faster R-CNN
Object Detection, Faster R-CNN
R-CNN
Object Detection, R-CNN
Object Detection이란
Object Detection,1-stage Detector,2-stage Detector
MobileNet, SqueezeNet, DenseNet
MobileNet, SqueezeNet, DenseNet
Inception v1,v2,v3
Inception, 1x1 Conv, GoogleNet
ZFNet & Network in Network
LeNet, AlexNet
LeNet & AlexNet
LeNet, AlexNet
(발표 자료) CNN
Convolutional Neural Network, ResNet, DenseNet
DenseNet 구현
Dense Unit, Dense & Transition Layer, Dense Net
ResNet 구현
Residual Unit, Residual Layer, Residual Net
Vanilla CNN 구현
Basic of Convolutional Neural Network