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/lsc-1/pecola
공식 코드https://github.com/lsh0520/rgcl
공식 코드Let Invariant Rationale Discovery Inspire Graph Contrastive Learning
https://github.com/lth14/targeted-supcon
공식 코드Targeted Supervised Contrastive Learning for Long-Tailed Recognition
https://github.com/lucas-rbnt/drim
공식 코드DRIM: Learning Disentangled Representations from Incomplete Multimodal Healthcare Data
https://github.com/lucasdedieu/noiseresilienthistopathology
공식 코드Contrastive-Based Deep Embeddings for Label Noise-Resilient Histopathology Image Classification
https://github.com/lucenzhong/tpld
공식 코드A Task-oriented Dialog Model with Task-progressive and Policy-aware Pre-training
https://github.com/luchixiang/pcrl
공식 코드https://github.com/ludanruan/clip4vla
공식 코드Accommodating Audio Modality in CLIP for Multimodal Processing
https://github.com/ludles/credanno
공식 코드Reducing Annotation Need in Self-Explanatory Models for Lung Nodule Diagnosis
https://github.com/luffy03/large-scale-medical
공식 코드Large-Scale 3D Medical Image Pre-training with Geometric Context Priors
https://github.com/luffy03/voco
공식 코드VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis
https://github.com/lujunru/tranclr
공식 코드Event-Centric Question Answering via Contrastive Learning and Invertible Event Transformation
https://github.com/lukahhcm/cultureclip
공식 코드https://github.com/luksysu/pascl
공식 코드https://github.com/lumos0507/hp-mcore
공식 코드Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regression
https://github.com/lunn88/tak-semi
공식 코드https://github.com/luoxiaoheics/cobe
공식 코드Mere Contrastive Learning for Cross-Domain Sentiment Analysis
https://github.com/luyug/GC-DPR
공식 코드Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup
https://github.com/luyug/GradCache
공식 코드Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup
https://github.com/lvkd84/graphfp
공식 코드Fragment-based Pretraining and Finetuning on Molecular Graphs
https://github.com/lx709/reobench
공식 코드REOBench: Benchmarking Robustness of Earth Observation Foundation Models
https://github.com/lxirich/mm-retinal
공식 코드MM-Retinal V2: Transfer an Elite Knowledge Spark into Fundus Vision-Language Pretraining
https://github.com/lxk00/clap
공식 코드https://github.com/lxtgh/tube-link
공식 코드Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation
https://github.com/ly245422/sspl
공식 코드SemiPL: A Semi-supervised Method for Event Sound Source Localization
https://github.com/lyakaap/isc21-descriptor-track-1st
공식 코드https://github.com/lyh-hh/afire
공식 코드https://github.com/lyhdet/ov-3det
공식 코드Open-Vocabulary Point-Cloud Object Detection without 3D Annotation
https://github.com/lylylylylyly/simplefsre
공식 코드A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation Extraction
https://github.com/lynn-yu/dtclmapper
공식 코드DTCLMapper: Dual Temporal Consistent Learning for Vectorized HD Map Construction
https://github.com/lzh19961031/pdcr_uafr-mis
공식 코드Contrastive and Selective Hidden Embeddings for Medical Image Segmentation
https://github.com/lzhangbj/DualVar
공식 코드Inter-intra Variant Dual Representations forSelf-supervised Video Recognition
https://github.com/lzvv123456/contrastive-prototypical-prompt
공식 코드Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning
https://github.com/lzvv123456/steering-prototypes-with-prompt-tuning-for-rehearsal-free-continual-learning
공식 코드Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning
https://github.com/lzxlin/knn-bioel
공식 코드Improving Biomedical Entity Linking with Retrieval-enhanced Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.