https://github.com/fundamentalvision/unigrad
공식 코드Exploring the Equivalence of Siamese Self-Supervised Learning via A Unified Gradient Framework
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/futurexiang/ddae
공식 코드Denoising Diffusion Autoencoders are Unified Self-supervised Learners
https://github.com/fuxiaoliu/documentclip
공식 코드DocumentCLIP: Linking Figures and Main Body Text in Reflowed Documents
https://github.com/fuying-wang/mgca
공식 코드Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning
https://github.com/fwu11/mcc
공식 코드Masked Collaborative Contrast for Weakly Supervised Semantic Segmentation
https://github.com/g-h-li/idfree
공식 코드https://github.com/gabolsgabs/contrastive-data-cleansing
공식 코드Data Cleansing with Contrastive Learning for Vocal Note Event Annotations
https://github.com/gaingod-xu/acmlproject
공식 코드https://github.com/galsang/SG-BERT
공식 코드Self-Guided Contrastive Learning for BERT Sentence Representations
https://github.com/gaoangw/hscl
공식 코드Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection
https://github.com/gaohaozhi/DE-TSMCL
공식 코드Distillation Enhanced Time Series Forecasting Network with Momentum Contrastive Learning
https://github.com/gaojingsheng/clucdd
공식 코드https://github.com/gaojun4ever/swcc4event
공식 코드https://github.com/gaopengcuhk/ballad
공식 코드A Simple Long-Tailed Recognition Baseline via Vision-Language Model
https://github.com/gaoren002/Anomaly-multiclassification
공식 코드Anomaly Multi-classification in Industrial Scenarios: Transferring Few-shot Learning to a New Task
https://github.com/gayanku/pamc
공식 코드Efficient block contrastive learning via parameter-free meta-node approximation
https://github.com/ge-xing/hybridmim
공식 코드HybridMIM: A Hybrid Masked Image Modeling Framework for 3D Medical Image Segmentation
https://github.com/geekjuruo/lead
공식 코드Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checking
https://github.com/geekjuruo/probexpan
공식 코드Contrastive Learning with Hard Negative Entities for Entity Set Expansion
https://github.com/generative-intelligence-lab/modelverse
공식 코드https://github.com/genjib/avsiam
공식 코드Siamese Vision Transformers are Scalable Audio-visual Learners
https://github.com/georgia-tech-synergy-lab/clamp-vit
공식 코드CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs
https://github.com/geox-lab/false
공식 코드https://github.com/geox-lab/grass
공식 코드https://github.com/geriskenderi/graph-jepa
공식 코드Graph-level Representation Learning with Joint-Embedding Predictive Architectures
https://github.com/gfmei/softclu
공식 코드Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding
https://github.com/ghost-signal/myna
공식 코드Myna: Masking-Based Contrastive Learning of Musical Representations
https://github.com/ghrua/ccpr_release
공식 코드https://github.com/giakoumoglou/distillers
공식 코드https://github.com/giakoumoglou/synco
공식 코드https://github.com/gianlucarloni/crocodile
공식 코드CROCODILE: Causality aids RObustness via COntrastive DIsentangled LEarning
https://github.com/giataile/realoecl
공식 코드Understanding normalization in contrastive representation learning and out-of-distribution detection
https://github.com/gimpong/AAAI22-MeCoQ
공식 코드Contrastive Quantization with Code Memory for Unsupervised Image Retrieval
https://github.com/gimpong/MM23-MISSRec
공식 코드https://github.com/gimpong/WWW22-HCQ
공식 코드Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval
https://github.com/ginkoeric/self-supervised-graph-pre-training-for-emoji
공식 코드Unleashing the Power of Emojis in Texts via Self-supervised Graph Pre-Training
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.