https://github.com/hannibal046/nmt_with_contrastive_memories
공식 코드Neural Machine Translation with Contrastive Translation Memories
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/hanshanley/tata
공식 코드TATA: Stance Detection via Topic-Agnostic and Topic-Aware Embeddings
https://github.com/hansonchen1996/mmgl
공식 코드https://github.com/hanyang-hcc-lab/lahn
공식 코드https://github.com/hao1635/ascon
공식 코드ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising
https://github.com/haohang96/bingo
공식 코드Bag of Instances Aggregation Boosts Self-supervised Distillation
https://github.com/haoliu-cola/cola
공식 코드Graph Contrastive Learning Meets Graph Meta Learning: A Unified Method for Few-shot Node Tasks
https://github.com/haon-chen/convaug
공식 코드Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation
https://github.com/haonan3/spgcl
공식 코드Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graph
https://github.com/haoosz/cipr
공식 코드https://github.com/haoqing-wang/infocl
공식 코드Rethinking Minimal Sufficient Representation in Contrastive Learning
https://github.com/haoranzhuexplorer/ad-l-jepa-release
공식 코드https://github.com/haotangxjtu/MSCL
공식 코드Multi-Sample based Contrastive Loss for Top-k Recommendation
https://github.com/haotiansun14/amorlip
공식 코드AmorLIP: Efficient Language-Image Pretraining via Amortization
https://github.com/haoyu-xie/prcl
공식 코드Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations
https://github.com/happypointer/multicbr
공식 코드MultiCBR: Multi-view Contrastive Learning for Bundle Recommendation
https://github.com/harsh9524/coca
공식 코드Capsule Network based Contrastive Learning of Unsupervised Visual Representations
https://github.com/hashmatshadab/hsat
공식 코드Hierarchical Self-Supervised Adversarial Training for Robust Vision Models in Histopathology
https://github.com/hassounlab/boost-rs
공식 코드https://github.com/havelhakimi/TLA
공식 코드Modeling Text-Label Alignment for Hierarchical Text Classification
https://github.com/haydenyu/mm-point
공식 코드MM-Point: Multi-View Information-Enhanced Multi-Modal Self-Supervised 3D Point Cloud Understanding
https://github.com/hbzju/pico
공식 코드PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning
https://github.com/hci-unihd/cl-tsne-umap
공식 코드https://github.com/hcplab-sysu/personsearch-ctlg
공식 코드Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search
https://github.com/hduc-le/simcpsr
공식 코드SimCPSR: Simple Contrastive Learning for Paper Submission Recommendation System
https://github.com/he-lingfeng/roi-extraction
공식 코드Weakly-supervised ROI extraction method based on contrastive learning for remote sensing images
https://github.com/heavenhellchen/recse
공식 코드reCSE: Portable Reshaping Features for Sentence Embedding in Self-supervised Contrastive Learning
https://github.com/hecoding/hyper-modulation
공식 코드Transferring Unconditional to Conditional GANs with Hyper-Modulation
https://github.com/hedongxiao-tju/E2Neg
공식 코드https://github.com/hegehongcha/slide-acl2024
공식 코드SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues Evaluation
https://github.com/helenqu/connect-later
공식 코드Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations
https://github.com/hello-jinwoo/LOVEU-CVPR2021
공식 코드Winning the CVPR'2021 Kinetics-GEBD Challenge: Contrastive Learning Approach
https://github.com/helloworldlty/muse-gnn
공식 코드MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data
https://github.com/henggao12/oal
공식 코드https://github.com/hengyicai/ContrastiveLearning4Dialogue
공식 코드Group-wise Contrastive Learning for Neural Dialogue Generation
https://github.com/henrywjl/icon
공식 코드Grounding Bodily Awareness in Visual Representations for Efficient Policy Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.