https://github.com/liang-tian-tian/mgcot
공식 코드Multi-Graph Co-Training for Capturing User Intent in Session-based Recommendation
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/liangcici/CITL-VLN
공식 코드Contrastive Instruction-Trajectory Learning for Vision-Language Navigation
https://github.com/liangyianita/mcd-dd
공식 코드https://github.com/liaochengcsu/bce-net
공식 코드https://github.com/liaoeuan/sincalignnet
공식 코드https://github.com/libeibei95/CMI
공식 코드Improving Micro-video Recommendation via Contrastive Multiple Interests
https://github.com/lichen14/tower
공식 코드https://github.com/lifangda01/adaptivesupervisedpatchnce
공식 코드https://github.com/ligerfotis/mvitac
공식 코드Multimodal Visual-Tactile Representation Learning through Self-Supervised Contrastive Pre-Training
https://github.com/light-47/ida
공식 코드Intermediate Domain-guided Adaptation for Unsupervised Chorioallantoic Membrane Vessel Segmentation
https://github.com/lightchen233/gl-clef
공식 코드https://github.com/lightonai/contrastive-embeddings-for-neural-architectures
공식 코드https://github.com/lijfrank-open/jmcppi
공식 코드Joint Masked Reconstruction and Contrastive Learning for Mining Interactions Between Proteins
https://github.com/lijiefan/advcl
공식 코드When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?
https://github.com/lijincm/CoCa
공식 코드https://github.com/lijy373/cclis
공식 코드Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation Distillation
https://github.com/lileicv/PDEN
공식 코드Progressive Domain Expansion Network for Single Domain Generalization
https://github.com/limanling/clip-event
공식 코드CLIP-Event: Connecting Text and Images with Event Structures
https://github.com/lina-luck/semantic_concept_embeddings
공식 코드Distilling Semantic Concept Embeddings from Contrastively Fine-Tuned Language Models
https://github.com/lingjzhu/charsiu
공식 코드Phone-to-audio alignment without text: A Semi-supervised Approach
https://github.com/lingjzhu/spoken_sent_embedding
공식 코드Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings
https://github.com/linglix/scl-lle
공식 코드Semantically Contrastive Learning for Low-light Image Enhancement
https://github.com/linhanz/mderank
공식 코드MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction
https://github.com/link-li/clmlf
공식 코드CLMLF:A Contrastive Learning and Multi-Layer Fusion Method for Multimodal Sentiment Detection
https://github.com/linuxsino/rppg-mae
공식 코드rPPG-MAE: Self-supervised Pre-training with Masked Autoencoders for Remote Physiological Measurement
https://github.com/linuxsino/visual-text-mg
공식 코드https://github.com/linwenye/light-moco
공식 코드Establishing a stronger baseline for lightweight contrastive models
https://github.com/linxi159/ICGS
공식 코드https://github.com/linxi1c/sspd
공식 코드Self-similarity Prior Distillation for Unsupervised Remote Physiological Measurement
https://github.com/linxin0/low_light_rainy
공식 코드Dual Degradation Representation for Joint Deraining and Low-Light Enhancement in the Dark
https://github.com/linyanglee/knn-bert
공식 코드KNN-BERT: Fine-Tuning Pre-Trained Models with KNN Classifier
https://github.com/lionellee9089/metamask
공식 코드MetaMask: Revisiting Dimensional Confounder for Self-Supervised Learning
https://github.com/lionellee9089/metaug
공식 코드https://github.com/liruiw/dec-ssl
공식 코드Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?
https://github.com/lisacoiffard/aurora-xcon
공식 코드Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity
https://github.com/lithium770/Unsupervised-Person-Re-identification-with-Stochastic-Training-Strategy
공식 코드Unsupervised Person Re-identification with Stochastic Training Strategy
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.