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/valentinovito/asymmetric-cl
공식 코드An Asymmetric Contrastive Loss for Handling Imbalanced Datasets
https://github.com/valeoai/also
공식 코드ALSO: Automotive Lidar Self-supervision by Occupancy estimation
https://github.com/vandrw/lostpaw-transformer
공식 코드LostPaw: Finding Lost Pets using a Contrastive Learning-based Transformer with Visual Input
https://github.com/vanint/core-tuning
공식 코드https://github.com/vannguyennd/livuitcl
공식 코드https://github.com/vano1205/efficientcl
공식 코드Efficient Contrastive Learning via Novel Data Augmentation and Curriculum Learning
https://github.com/veason-silverbullet/unitrec
공식 코드https://github.com/ventr1c/res-gcl
공식 코드https://github.com/veronicium/anchordr
공식 코드https://github.com/vfeofanov/mantis
공식 코드Mantis: Lightweight Calibrated Foundation Model for User-Friendly Time Series Classification
https://github.com/vibalcam/glofnd
공식 코드Discovering Global False Negatives On the Fly for Self-supervised Contrastive Learning
https://github.com/vignywang/samfeat
공식 코드Segment Anything Model is a Good Teacher for Local Feature Learning
https://github.com/viktoraxelsen/cle-tfe
공식 코드https://github.com/viktoraxelsen/mh-net
공식 코드Revolutionizing Encrypted Traffic Classification with MH-Net: A Multi-View Heterogeneous Graph Model
https://github.com/viktoraxelsen/tgsl
공식 코드Time-aware Graph Structure Learning via Sequence Prediction on Temporal Graphs
https://github.com/vinayak1/gcbs
공식 코드Global Contrastive Batch Sampling via Optimization on Sample Permutations
https://github.com/vincent-zhq/unis-mmc
공식 코드UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning
https://github.com/vios-s/ldm-phrase-grounding
공식 코드Zero-Shot Medical Phrase Grounding with Off-the-shelf Diffusion Models
https://github.com/virtuosoresearch/tree-data-augmentation
공식 코드https://github.com/visresearch/MultipleObjectStitching
공식 코드Multiple Object Stitching for Unsupervised Representation Learning
https://github.com/visresearch/aps
공식 코드https://github.com/visresearch/mgc
공식 코드Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning
https://github.com/visresearch/patchmix
공식 코드https://github.com/visual-ds/plausible-nlp-explanations
공식 코드https://github.com/visualaikhu/keyword-detr
공식 코드https://github.com/vita-epfl/social-nce
공식 코드Reproducibility Report: Contrastive Learning of Socially-aware Motion Representations
https://github.com/vita-group/layergraftedpretraining_iclr23
공식 코드https://github.com/vita-group/mak
공식 코드Improving Contrastive Learning on Imbalanced Seed Data via Open-World Sampling
https://github.com/vittoriogiammarino/c-laifo
공식 코드Visually Robust Adversarial Imitation Learning from Videos with Contrastive Learning
https://github.com/vityavitalich/mlem
공식 코드MLEM: Generative and Contrastive Learning as Distinct Modalities for Event Sequences
https://github.com/vivekmyers/contrastive_metrics
공식 코드https://github.com/vivekmyers/contrastive_planning
공식 코드Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference
https://github.com/vkinakh/mv-mr
공식 코드MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation
https://github.com/vkinakh/scatsimclr
공식 코드https://github.com/vkola-lab/tmi2022
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.