https://github.com/ZJU-DAILY/MQA
공식 코드An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models
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/ZJU-DAILY/Snoopy
공식 코드Snoopy: Effective and Efficient Semantic Join Discovery via Proxy Columns
https://github.com/ZJU-Fangyin/KCL
공식 코드Molecular Contrastive Learning with Chemical Element Knowledge Graph
https://github.com/Zhang-xiaokun/MACL
공식 코드Rethinking Contrastive Learning in Session-based Recommendation
https://github.com/ZhangYuanhan-AI/OmniBenchmark
공식 코드Benchmarking Omni-Vision Representation through the Lens of Visual Realms
https://github.com/ZhengyaoFang/WeCromCL
공식 코드https://github.com/ZhiyuanDang/DCDC
공식 코드https://github.com/Zhong-Zhengyi/SacFL-Code
공식 코드SacFL: Self-Adaptive Federated Continual Learning for Resource-Constrained End Devices
https://github.com/a-hou/gtca
공식 코드GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning
https://github.com/aaronz345/tcsinger2
공식 코드TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis
https://github.com/aaupadhy/AmCLR
공식 코드AmCLR: Unified Augmented Learning for Cross-Modal Representations
https://github.com/abedicodes/scl-dad
공식 코드Supervised Contrastive Learning for Detecting Anomalous Driving Behaviours from Multimodal Videos
https://github.com/abidlabs/contrastive_vae
공식 코드Contrastive Variational Autoencoder Enhances Salient Features
https://github.com/aburns4/UnsupDisent
공식 코드Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions
https://github.com/acasamitjana/SynthByReg
공식 코드Synth-by-Reg (SbR): Contrastive learning for synthesis-based registration of paired images
https://github.com/acharkq/molca
공식 코드MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter
https://github.com/adacheng/product_taxonomy_expansion
공식 코드Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors Supervision
https://github.com/adap/flower
공식 코드https://github.com/adaptivemotorcontrollab/cebra
공식 코드Time-series attribution maps with regularized contrastive learning
https://github.com/adirrahamim/claf
공식 코드Robustness through Cognitive Dissociation Mitigation in Contrastive Adversarial Training
https://github.com/adxcreative/rice
공식 코드Cross-view Semantic Alignment for Livestreaming Product Recognition
https://github.com/agave233/GeomGCL
공식 코드GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction
https://github.com/agent-lab/diffusion-integer-programming
공식 코드Effective Generation of Feasible Solutions for Integer Programming via Guided Diffusion
https://github.com/agopal42/ctcae
공식 코드Contrastive Training of Complex-Valued Autoencoders for Object Discovery
https://github.com/aheuillet/nasiam
공식 코드NASiam: Efficient Representation Learning using Neural Architecture Search for Siamese Networks
https://github.com/ahnobari/LInK
공식 코드https://github.com/ai-agi/hicl
공식 코드https://github.com/ai-hpc-research-team/protfad
공식 코드ProtFAD: Introducing function-aware domains as implicit modality towards protein function prediction
https://github.com/ai4ce/Contrastive-SPARE3D
공식 코드Self-supervised Spatial Reasoning on Multi-View Line Drawings
https://github.com/ai4cts/e2usd
공식 코드E2USD: Efficient-yet-effective Unsupervised State Detection for Multivariate Time Series
https://github.com/ai4science-westlakeu/t_scend
공식 코드https://github.com/aielte-research/MedSegPretrainImageNet
공식 코드Enhancing pretraining efficiency for medical image segmentation via transferability metrics
https://github.com/aigeeksgroup/mmclip
공식 코드MMCLIP: Cross-modal Attention Masked Modelling for Medical Language-Image Pre-Training
https://github.com/aim-se/da4rec
공식 코드https://github.com/aimagelab/code
공식 코드Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities
https://github.com/aimagelab/open-fashion-clip
공식 코드OpenFashionCLIP: Vision-and-Language Contrastive Learning with Open-Source Fashion Data
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.