https://github.com/Somedaywilldo/AutoGCL
공식 코드AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators
Papers with Code 아카이브
Contrastive Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 4
- 보존된 평가 기록
- 17
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>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/SongweiGe/Contrastive-Learning-with-Non-Semantic-Negatives
공식 코드Robust Contrastive Learning Using Negative Samples with Diminished Semantics
https://github.com/Sootung/RAMer
공식 코드https://github.com/SpencerWhitehead/novelvqa
공식 코드Separating Skills and Concepts for Novel Visual Question Answering
https://github.com/SsnL/align_uniform
공식 코드https://github.com/SubmissionsIn/MFLVC
공식 코드Multi-level Feature Learning for Contrastive Multi-view Clustering
https://github.com/SwinTransformer/Feature-Distillation
공식 코드Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation
https://github.com/Synerise/cleora
공식 코드Cleora: A Simple, Strong and Scalable Graph Embedding Scheme
https://github.com/SysCV/qdtrack
공식 코드Quasi-Dense Similarity Learning for Multiple Object Tracking
https://github.com/THU-KEG/CLEVE
공식 코드https://github.com/THU-luvision/OmniSeg3D
공식 코드OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning
https://github.com/THUDM/GCC
공식 코드GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
https://github.com/THUDM/SelfKG
공식 코드https://github.com/TJU-DRL-LAB/self-supervised-rl/tree/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm
공식 코드Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning
https://github.com/TOM-tym/Learn-to-Imagine
공식 코드Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled Data
https://github.com/TRAILab/ST-SLidR
공식 코드Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss
https://github.com/TaoZhen1110/MFD
공식 코드Unveiling Large Language Models Generated Texts: A Multi-Level Fine-Grained Detection Framework
https://github.com/Tawkat/Arabic-CL-Benchmark
공식 코드A Benchmark Study of Contrastive Learning for Arabic Social Meaning
https://github.com/TencentAILabHealthcare/Few-shot-WSI
공식 코드https://github.com/TengShi-RUC/CFRAG
공식 코드Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generation
https://github.com/TengdaHan/CoCLR
공식 코드Self-supervised Co-training for Video Representation Learning
https://github.com/Terminator8758/CAP-master
공식 코드Camera-aware Proxies for Unsupervised Person Re-Identification
https://github.com/Thinklab-SJTU/ThinkMatch
공식 코드https://github.com/ThomasYerxa/mmcr
공식 코드Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations
https://github.com/TsungWeiTsai/MiCE
공식 코드MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering
https://github.com/UARK-AICV/VLCAP
공식 코드VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning
https://github.com/UCDvision/CGC
공식 코드https://github.com/UKPLab/acl2024-triple-encoders
공식 코드Triple-Encoders: Representations That Fire Together, Wire Together
https://github.com/UKPLab/arxiv2024-modular-sentence-encoders
공식 코드Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment
https://github.com/UMBCvision/ISD
공식 코드ISD: Self-Supervised Learning by Iterative Similarity Distillation
https://github.com/USTBInnovationPark/Frequency-masked-Embedding-Inference
공식 코드https://github.com/UmarKhalidcs/RODD
공식 코드RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection
https://github.com/VCG-team/DiffSegmenter
공식 코드Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter
https://github.com/VDIGPKU/ContinualContrastiveLearning
공식 코드https://github.com/VITA-Group/Adversarial-Contrastive-Learning
공식 코드https://github.com/VITA-Group/SDCLR
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.