https://github.com/pfdp0/ContrasTR
공식 코드Contrastive Learning for Multi-Object Tracking with Transformers
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/pfnet-research/label-efficient-brain-tumor-segmentation
공식 코드Label-Efficient Multi-Task Segmentation using Contrastive Learning
https://github.com/phd-lanyu/gtc
공식 코드GTC: GNN-Transformer Co-contrastive Learning for Self-supervised Heterogeneous Graph Representation
https://github.com/phd-lanyu/motifs-res
공식 코드Motifs-based Recommender System via Hypergraph Convolution and Contrastive Learning
https://github.com/phdymz/pointclm
공식 코드PointCLM: A Contrastive Learning-based Framework for Multi-instance Point Cloud Registration
https://github.com/phil-fradkin/contrastive_rna
공식 코드https://github.com/philip-mueller/lovt
공식 코드Joint Learning of Localized Representations from Medical Images and Reports
https://github.com/phoebussi/mmbs
공식 코드Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning
https://github.com/phycvgan/dystyle
공식 코드DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing
https://github.com/physiologicailab/sam-cl
공식 코드Self-adversarial Multi-scale Contrastive Learning for Semantic Segmentation of Thermal Facial Images
https://github.com/piecezhang/mpt-catablur
공식 코드https://github.com/pimed/provicnet
공식 코드Prostate-Specific Foundation Models for Enhanced Detection of Clinically Significant Cancer
https://github.com/pku-ai-edge/corro
공식 코드Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning
https://github.com/pku-icst-mipl/finedefics_iclr2025
공식 코드https://github.com/pku-icst-mipl/sim-trans_acmmm2022
공식 코드SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorization
https://github.com/pku-ml/adainf
공식 코드https://github.com/pku-ml/advnotrealfeatures
공식 코드https://github.com/pku-ml/architecturemattersgcl
공식 코드Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning
https://github.com/pku-ml/clip-help-simclr
공식 코드https://github.com/pku-ml/clustermim
공식 코드On the Role of Discrete Tokenization in Visual Representation Learning
https://github.com/pku-ml/contranorm
공식 코드ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond
https://github.com/pku-ml/dynacl
공식 코드Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning
https://github.com/pku-ml/message-passing-contrastive-learning
공식 코드A Message Passing Perspective on Learning Dynamics of Contrastive Learning
https://github.com/pku-ml/non_neg
공식 코드https://github.com/pku-ml/projector_theory
공식 코드https://github.com/pku-ml/rank-differential-mechanism
공식 코드https://github.com/pku-yuangroup/languagebind
공식 코드https://github.com/pkunlp-icler/cofftea
공식 코드Coarse-to-Fine Dual Encoders are Better Frame Identification Learners
https://github.com/pkunlp-icler/scl-rai
공식 코드https://github.com/pliang279/factorcl
공식 코드Factorized Contrastive Learning: Going Beyond Multi-view Redundancy
https://github.com/plus-rkwitt/py_supcon_vs_ce
공식 코드https://github.com/pmzzs/JigMark
공식 코드JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits
https://github.com/pnborchert/multirep
공식 코드https://github.com/poodarchu/SelfSup/tree/master/examples/simo
공식 코드EqCo: Equivalent Rules for Self-supervised Contrastive Learning
https://github.com/porthok/RL_Simple_Shapes
공식 코드Zero-shot cross-modal transfer of Reinforcement Learning policies through a Global Workspace
https://github.com/ppwangyc/wave
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.