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/conghuihu/ucdir
공식 코드Feature Representation Learning for Unsupervised Cross-domain Image Retrieval
https://github.com/conormdurkan/lfi
공식 코드https://github.com/contextualai/clair_and_apo
공식 코드https://github.com/cooplo/picl
공식 코드PICL: Physics Informed Contrastive Learning for Partial Differential Equations
https://github.com/copenlu/TESTED/blob/main/README.md
공식 코드Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection
https://github.com/cpark88/CGRec
공식 코드https://github.com/cptdiaos/multi-roi
공식 코드Multi-RoI Human Mesh Recovery with Camera Consistency and Contrastive Losses
https://github.com/craigleili/srfeat
공식 코드SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondence
https://github.com/crazy-jack/cclk-release
공식 코드https://github.com/crazy-jack/cl-infonce
공식 코드https://github.com/crealabs/enhanced-bge-m3-with-clp-and-moe
공식 코드https://github.com/cripac-dig/getral
공식 코드Adversarial Contrastive Learning for Evidence-aware Fake News Detection with Graph Neural Networks
https://github.com/cristianopatricio/unsupervised-contrastive-cond-diff
공식 코드Unsupervised Contrastive Analysis for Salient Pattern Detection using Conditional Diffusion Models
https://github.com/cruiseresearchgroup/TSCP2
공식 코드Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding
https://github.com/cruiseresearchgroup/cocoa
공식 코드https://github.com/cruiseresearchgroup/forecasting-on-new-roads
공식 코드Traffic Forecasting on New Roads Using Spatial Contrastive Pre-Training (SCPT)
https://github.com/crystalsixone/vln-goat
공식 코드https://github.com/cs-sail/tensor-mv-gcl
공식 코드https://github.com/cscyqj/miccai23-protocontra-sfda
공식 코드https://github.com/cseeyangchen/c2vl
공식 코드https://github.com/cseeyangchen/dt-pose
공식 코드Towards Robust and Realistic Human Pose Estimation via WiFi Signals
https://github.com/csguoh/kd-ltr
공식 코드One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer
https://github.com/cshaitao/jtr
공식 코드Constructing Tree-based Index for Efficient and Effective Dense Retrieval
https://github.com/csjywu1/gdndgp
공식 코드https://github.com/csm9493/PNR
공식 코드Regularizing with Pseudo-Negatives for Continual Self-Supervised Learning
https://github.com/cstankonrad/long_llama
공식 코드Focused Transformer: Contrastive Training for Context Scaling
https://github.com/csuhan/opendet2
공식 코드Expanding Low-Density Latent Regions for Open-Set Object Detection
https://github.com/cszhangzhen/graphcta
공식 코드Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation
https://github.com/ct4rec/ct4rec
공식 코드CT4Rec: Simple yet Effective Consistency Training for Sequential Recommendation
https://github.com/cucl-2/dc-seg
공식 코드DC-Seg: Disentangled Contrastive Learning for Brain Tumor Segmentation with Missing Modalities
https://github.com/cuixuage/KDDCup2022-ESCI
공식 코드ZhichunRoad at Amazon KDD Cup 2022: MultiTask Pre-Training for E-Commerce Product Search
https://github.com/cunningham-lab/augcoda
공식 코드Data Augmentation for Compositional Data: Advancing Predictive Models of the Microbiome
https://github.com/cv-rits/coarse3d
공식 코드COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation
https://github.com/cvc-lab/patch-subspace-learning-autoencoder
공식 코드Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processing
https://github.com/cvi-szu/ccam
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.