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/nuochenpku/sscl
공식 코드Alleviating Over-smoothing for Unsupervised Sentence Representation
https://github.com/nustm/cpnc
공식 코드Commonsense Knowledge Graph Completion Via Contrastive Pretraining and Node Clustering
https://github.com/nvtien457/nearbypatchcl
공식 코드https://github.com/nynu-bdai/ahnpl
공식 코드https://github.com/nyushcs/gaugllm
공식 코드GAugLLM: Improving Graph Contrastive Learning for Text-Attributed Graphs with Large Language Models
https://github.com/nyushcs/uniglm
공식 코드UniGLM: Training One Unified Language Model for Text-Attributed Graph Embedding
https://github.com/nzl5116190/basisformer
공식 코드BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis
https://github.com/oceanlvr/protoau
공식 코드Prototypical Contrastive Learning through Alignment and Uniformity for Recommendation
https://github.com/oetu/mmcl-ecg-cmr
공식 코드https://github.com/oezyurty/cluda
공식 코드Contrastive Learning for Unsupervised Domain Adaptation of Time Series
https://github.com/oezyurty/kcqrl
공식 코드Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing
https://github.com/ofa-sys/chinese-clip
공식 코드Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese
https://github.com/ojss/c3lr
공식 코드https://github.com/ojss/samptransfer
공식 코드Self-Attention Message Passing for Contrastive Few-Shot Learning
https://github.com/okankop/Driver-Anomaly-Detection
공식 코드Driver Anomaly Detection: A Dataset and Contrastive Learning Approach
https://github.com/oliverhxh/skeletongcl
공식 코드Graph Contrastive Learning for Skeleton-based Action Recognition
https://github.com/omarerak/clad
공식 코드Contrastive Learning and Adversarial Disentanglement for Task-Oriented Semantic Communications
https://github.com/ondrejba/negative-sampling-icml-21
공식 코드The Impact of Negative Sampling on Contrastive Structured World Models
https://github.com/onlinehuazai/evit
공식 코드EViT: Privacy-Preserving Image Retrieval via Encrypted Vision Transformer in Cloud Computing
https://github.com/open-air-sun/viewpoint-bottleneck
공식 코드Pointly-supervised 3D Scene Parsing with Viewpoint Bottleneck
https://github.com/open-event-hub/event-enhanced_retrieval
공식 코드https://github.com/open-mmlab/OpenSelfSup
공식 코드Delving into Inter-Image Invariance for Unsupervised Visual Representations
https://github.com/open-mmlab/mmselfsup
공식 코드Delving into Inter-Image Invariance for Unsupervised Visual Representations
https://github.com/opengvlab/internvideo
공식 코드InternVideo: General Video Foundation Models via Generative and Discriminative Learning
https://github.com/opengvlab/internvideo2
공식 코드InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
https://github.com/opengvlab/lcl
공식 코드Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning
https://github.com/openlmlab/moss-rlhf
공식 코드Secrets of RLHF in Large Language Models Part II: Reward Modeling
https://github.com/openmicg/mcg
공식 코드https://github.com/opennlplab/fnac_avl
공식 코드Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning
https://github.com/opennlplab/tavgbench
공식 코드https://github.com/openrobotlab/himloco
공식 코드Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response
https://github.com/openspaceai/uvltrack
공식 코드Unifying Visual and Vision-Language Tracking via Contrastive Learning
https://github.com/optimization-ai/drrho-clip
공식 코드Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws
https://github.com/optimusprimus/salsa
공식 코드Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval
https://github.com/optml-group/claw-sat
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.