kjyong

See All 컴퓨터비전 딥러닝 경량화 KnowedgeDistillation Diffusion

ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models

ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models

OpenVLA: An Open-Source Vision-Language-Action Model

OpenVLA: An Open-Source Vision-Language-Action Model

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

MagicVideo: Efficient Video Generation With Latent Diffusion Models

MagicVideo: Efficient Video Generation With Latent Diffusion Models

Video Diffusion Models (VDM)

Video Diffusion Models (VDM)

ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models

ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models

OpenVLA: An Open-Source Vision-Language-Action Model

OpenVLA: An Open-Source Vision-Language-Action Model

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

MagicVideo: Efficient Video Generation With Latent Diffusion Models

MagicVideo: Efficient Video Generation With Latent Diffusion Models

Video Diffusion Models (VDM)

Video Diffusion Models (VDM)

InstantID: Zero-shot Identity Preserving Generation in Seconds

InstantID: Zero-shot Identity Preserving Generation in Seconds

SnapFusion: Text-to-Image Diffusion Model on Mobile
Devices within Two Seconds

SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds

LoRA: Low-Rank Adaptation of Large Language Models

LoRA: Low-Rank Adaptation of Large Language Models

Textual Inversion: An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

Textual Inversion: An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

DreamBooth: Fine Tuning Text-to-Image Diffusion Models
for Subject-Driven Generation

DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

LDM: High-Resolution Image Synthesis with Latent Diffusion Models

LDM: High-Resolution Image Synthesis with Latent Diffusion Models

VQ-VAE: Neural Discrete Representation Learning

VQ-VAE: Neural Discrete Representation Learning

컴퓨터비전

MAE와 MSE는 부호를 없애는데 어떻게 regression이 학습되는 걸까?

MAE와 MSE는 부호를 없애는데 어떻게 regression이 학습되는 걸까?

regression loss의 미분값에 대한 이해

왜 Re-Identification에서 GeM을 쓸까?

왜 Re-Identification에서 GeM을 쓸까?

GeM Pooling VS Max Pooling vs Average Pooling

컴퓨터비전딥러닝

[Knowledge Distillation] Learning from a Teacher using Unlabeled Data

[Knowledge Distillation] Learning from a Teacher using Unlabeled Data

Unlabelling 데이터를 활용하여 Teacher보다 똑똑한 Student 만들기

컴퓨터비전경량화딥러닝