https://github.com/tidiane-camaret/eegclip
공식 코드EEG-CLIP : Learning EEG representations from natural language descriptions
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/tigerchen52/love
공식 코드Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost
https://github.com/tigerchen52/pearl
공식 코드Learning High-Quality and General-Purpose Phrase Representations
https://github.com/tileb1/adasim
공식 코드Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learning
https://github.com/tinapan-pt/VideoMoCo
공식 코드VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples
https://github.com/tingjshen/urllm
공식 코드https://github.com/tingyu215/SECLA
공식 코드Weakly Supervised Face Naming with Symmetry-Enhanced Contrastive Loss
https://github.com/tjtp/kdar
공식 코드https://github.com/tjunlp-lab/pckmt
공식 코드Efficient Cluster-Based k-Nearest-Neighbor Machine Translation
https://github.com/tkipf/c-swm
공식 코드https://github.com/tokkiu/ecl
공식 코드Equivariant Contrastive Learning for Sequential Recommendation
https://github.com/tom99763/Contrastive-Bi-Projector-for-Unsupervised-Domain-Adaption
공식 코드https://github.com/tomaidd/nafm-official
공식 코드NaFM: Pre-training a Foundation Model for Small-Molecule Natural Products
https://github.com/tomguluson92/eraseanything
공식 코드EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers
https://github.com/tomoyoshki/focal
공식 코드https://github.com/toneyaya/cgformer
공식 코드Contrastive Grouping with Transformer for Referring Image Segmentation
https://github.com/tonyby/m3
공식 코드https://github.com/topogclaaai24/topogcl
공식 코드https://github.com/torpedo2648/pclmix
공식 코드https://github.com/toyotaresearchinstitute/remoteppg
공식 코드https://github.com/tpcd/dccl
공식 코드Dynamic Conceptional Contrastive Learning for Generalized Category Discovery
https://github.com/trangvu/guda
공식 코드https://github.com/trinhvg/impash
공식 코드IMPaSh: A Novel Domain-shift Resistant Representation for Colorectal Cancer Tissue Classification
https://github.com/trinhvg/moma
공식 코드https://github.com/trustedllm/autoregembed
공식 코드Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment
https://github.com/trustmlrg/transpoison
공식 코드https://github.com/tsbiosky/PointACL
공식 코드https://github.com/tshu-w/ublocker
공식 코드https://github.com/tshu-w/uniblocker
공식 코드https://github.com/tsinghua-fib-lab/agentstealth
공식 코드AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text
https://github.com/tsinghua-fib-lab/clsr
공식 코드Disentangling Long and Short-Term Interests for Recommendation
https://github.com/tsinghua-fib-lab/dcn
공식 코드Mutual Harmony: Sequential Recommendation with Dual Contrastive Network
https://github.com/tsinghua-fib-lab/sigir24-frec
공식 코드https://github.com/tsinghua-fib-lab/urbankg-knowcl
공식 코드Knowledge-infused Contrastive Learning for Urban Imagery-based Socioeconomic Prediction
https://github.com/tsingz0/fedtgp
공식 코드https://github.com/tuananhbui89/ASCL
공식 코드Understanding and Achieving Efficient Robustness with Adversarial Supervised Contrastive Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.