https://github.com/judydnguyen/pardon-feddg
공식 코드PARDON: Privacy-Aware and Robust Federated Domain Generalization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Contrastive Learning is a deep learning technique for unsupervised representation learning. The goal is to learn a representation of data such that similar instances are close together in the representation space, while dissimilar instances are far apart.
It has been shown to be effective in various computer vision and natural language processing tasks, including image retrieval, zero-shot learning, and cross-modal retrieval. In these tasks, the learned representations can be used as features for downstream tasks such as classification and clustering.
<span style="color:grey; opacity: 0.6">(Image credit: Schroff et al. 2015)</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
PARDON: Privacy-Aware and Robust Federated Domain Generalization
Contrastive Learning for Sleep Staging based on Inter Subject Correlation
CATALOG: A Camera Trap Language-guided Contrastive Learning Model
Similarity Contrastive Estimation for Self-Supervised Soft Contrastive Learning
Lesion-Aware Contrastive Representation Learning for Histopathology Whole Slide Images Analysis
CropMix: Sampling a Rich Input Distribution via Multi-Scale Cropping
Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization
Relational Self-supervised Distillation with Compact Descriptors for Image Copy Detection
Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification
Self-Supervised Contrastive Learning for Long-term Forecasting
ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning
SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation
MAPConNet: Self-supervised 3D Pose Transfer with Mesh and Point Contrastive Learning
Sounding Video Generator: A Unified Framework for Text-guided Sounding Video Generation
Category Contrast for Unsupervised Domain Adaptation in Visual Tasks
Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning
RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks
Learning Representations with Contrastive Self-Supervised Learning for Histopathology Applications
FontGuard: A Robust Font Watermarking Approach Leveraging Deep Font Knowledge
DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph
Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning
Eliciting Structural and Semantic Global Knowledge in Unsupervised Graph Contrastive Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.