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/yuxiaochen1103/Hi-TRS
공식 코드Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning
https://github.com/yuxiaochen1103/fdt
공식 코드https://github.com/yuxiaw/empathic-similarity
공식 코드Can Machines Resonate with Humans? Evaluating the Emotional and Empathic Comprehension of LMs
https://github.com/yuyangw/MolCLR
공식 코드Molecular Contrastive Learning of Representations via Graph Neural Networks
https://github.com/yuyangw/iMolCLR
공식 코드https://github.com/yuzhimanhua/micol
공식 코드Metadata-Induced Contrastive Learning for Zero-Shot Multi-Label Text Classification
https://github.com/yvonneywu/statiocl
공식 코드StatioCL: Contrastive Learning for Time Series via Non-Stationary and Temporal Contrast
https://github.com/yxbian23/aLLM4TS
공식 코드Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning
https://github.com/yxgeee/SpCL
공식 코드Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
https://github.com/yxuansu/contrastive_search_is_what_you_need
공식 코드Contrastive Search Is What You Need For Neural Text Generation
https://github.com/yxuansu/tacl
공식 코드TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning
https://github.com/yy-ko/cash
공식 코드Enhancing Hyperedge Prediction with Context-Aware Self-Supervised Learning
https://github.com/yyk-wew/semanticmim
공식 코드https://github.com/yyliu01/auralsam2
공식 코드AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting
https://github.com/yyliu01/it2
공식 코드ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation
https://github.com/yyliu01/rpl
공식 코드Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation
https://github.com/yym6472/ConSERT
공식 코드ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer
https://github.com/yyuncong/tempclr
공식 코드TempCLR: Temporal Alignment Representation with Contrastive Learning
https://github.com/yz-wang/ucl-dehaze
공식 코드UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning
https://github.com/yzh0905/aecl-stc
공식 코드https://github.com/yzh0905/pota-stc
공식 코드Reliable Pseudo-labeling via Optimal Transport with Attention for Short Text Clustering
https://github.com/zackschen/CGP
공식 코드https://github.com/zaiwen/hncl-dti
공식 코드A Heterogeneous Network-based Contrastive Learning Approach for Predicting Drug-Target Interaction
https://github.com/zamanzadeh/CARLA
공식 코드CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection
https://github.com/zamanzadeh/DACAD
공식 코드DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series
https://github.com/zangzelin/code_ECCV2022_DLME
공식 코드https://github.com/zangzelin/code_diffaug
공식 코드https://github.com/zangzelin/code_usd
공식 코드USD: Unsupervised Soft Contrastive Learning for Fault Detection in Multivariate Time Series
https://github.com/zdaxie/PixPro
공식 코드https://github.com/zehong-wang/hgcml
공식 코드https://github.com/zek3r/icml2023
공식 코드Flexible Phase Dynamics for Bio-Plausible Contrastive Learning
https://github.com/zekarias-tilahun/SelfGNN
공식 코드Self-supervised Graph Neural Networks without explicit negative sampling
https://github.com/zengyan-97/cclm
공식 코드Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training
https://github.com/zerohd4869/sacl
공식 코드Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations
https://github.com/zerovl/zerovl
공식 코드Contrastive Vision-Language Pre-training with Limited Resources
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.