https://github.com/jiaw-z/fcstereo
공식 코드Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective
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/jiepku/partcrop
공식 코드A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability
https://github.com/jiepku/understand-ssl-part-aware
공식 코드Understanding Self-Supervised Pretraining with Part-Aware Representation Learning
https://github.com/jiequancui/Parametric-Contrastive-Learning
공식 코드https://github.com/jinfeng-xu/nlgcl
공식 코드NLGCL: Naturally Existing Neighbor Layers Graph Contrastive Learning for Recommendation
https://github.com/jinglin-liang/dddr
공식 코드https://github.com/jingqiangchen/concaps
공식 코드Transform, Contrast and Tell: Coherent Entity-Aware Multi-Image Captioning
https://github.com/jingwang18/silan
공식 코드https://github.com/jingwu6/extended-agriculture-vision-dataset
공식 코드https://github.com/jingxiaolun/tc-mgc
공식 코드TC-MGC: Text-Conditioned Multi-Grained Contrastive Learning for Text-Video Retrieval
https://github.com/jinhojsk515/ldmol
공식 코드LDMol: Text-to-Molecule Diffusion Model with Structurally Informative Latent Space
https://github.com/jinhseo/od-wscl
공식 코드Object Discovery via Contrastive Learning for Weakly Supervised Object Detection
https://github.com/jinhuiye/signcl
공식 코드Improving Gloss-free Sign Language Translation by Reducing Representation Density
https://github.com/jinpeng01/aig_cl
공식 코드Graph Enhanced Contrastive Learning for Radiology Findings Summarization
https://github.com/jinsuby/domclp
공식 코드DomCLP: Domain-wise Contrastive Learning with Prototype Mixup for Unsupervised Domain Generalization
https://github.com/jinweizzz/opencarbon
공식 코드https://github.com/jishengbai/audiolog
공식 코드AudioLog: LLMs-Powered Long Audio Logging with Hybrid Token-Semantic Contrastive Learning
https://github.com/jiuhaichen/florence-vl
공식 코드https://github.com/jizongFox/Self-paced-Contrastive-Learning
공식 코드Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels
https://github.com/jjwwczy/ContrastNet-Unsupervised-Feature-Learning-by-Autoencoder-and-Prototypical-Contrastive-Learning
공식 코드https://github.com/jjy961228/ConCSE
공식 코드ConCSE: Unified Contrastive Learning and Augmentation for Code-Switched Embeddings
https://github.com/jldbc/pybaseball
공식 코드https://github.com/joeyy5588/lacma
공식 코드LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following
https://github.com/jone1222/DG-Feature-Stylization
공식 코드Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization
https://github.com/jongdory/damt
공식 코드Domain Aware Multi-Task Pretraining of 3D Swin Transformer for T1-weighted Brain MRI
https://github.com/jongsuk1/equiav
공식 코드EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning
https://github.com/joshr17/HCL
공식 코드https://github.com/joshr17/IFM
공식 코드https://github.com/joshualpf/alignsal
공식 코드https://github.com/joycenerd/Saliency-Guided-Masking-for-ConvNets
공식 코드Masking Improves Contrastive Self-Supervised Learning for ConvNets, and Saliency Tells You Where
https://github.com/jpeper/gen_scl_nat
공식 코드Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive Structure
https://github.com/jpthu17/HBI
공식 코드Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning
https://github.com/jpthu17/emcl
공식 코드Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations
https://github.com/jsliam94/cmswinkan
공식 코드https://github.com/jsun57/mooss
공식 코드https://github.com/jswati31/gazeclr
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.