https://github.com/feipan664/IntraDA
공식 코드Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision
A deep learning approach for marine snow synthesis and removal
Domain Adaptation for Underwater Image Enhancement via Content and Style Separation
Magnetogram-to-Magnetogram: Generative Forecasting of Solar Evolution
An Unsupervised Domain Adaptation Scheme for Single-Stage Artwork Recognition in Cultural Sites
Memory-Guided Collaborative Attention for Nighttime Thermal Infrared Image Colorization
Dynamic Conditional Optimal Transport through Simulation-Free Flows
Photorealistic and Identity-Preserving Image-Based Emotion Manipulation with Latent Diffusion Models
GANILLA: Generative Adversarial Networks for Image to Illustration Translation
WAIT: Feature Warping for Animation to Illustration video Translation using GANs
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation
LBM: Latent Bridge Matching for Fast Image-to-Image Translation
MaskSketch: Unpaired Structure-guided Masked Image Generation
Variational Interaction Information Maximization for Cross-domain Disentanglement
CoPE: Conditional image generation using Polynomial Expansions
Cross-modal tumor segmentation using generative blending augmentation and self training
A Unified Generative Framework for Realistic Lidar Simulation in Autonomous Driving Systems
A Unified Generative Framework for Realistic Lidar Simulation in Autonomous Driving Systems
Computing high-dimensional optimal transport by flow neural networks
Melanoma Detection using Adversarial Training and Deep Transfer Learning
Synthesis of COVID-19 Chest X-rays using Unpaired Image-to-Image Translation
Can We Find Neurons that Cause Unrealistic Images in Deep Generative Networks?
Time-of-Day Neural Style Transfer for Architectural Photographs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.