https://github.com/mhamilton723/DenseAV
공식 코드Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language
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/mhw32/temperature-as-uncertainty-public
공식 코드https://github.com/miaomiao-cai2/kdd2024-paac
공식 코드Popularity-Aware Alignment and Contrast for Mitigating Popularity Bias
https://github.com/miccaiif/ins
공식 코드https://github.com/michaeltrs/deepsatmodels
공식 코드Context-self contrastive pretraining for crop type semantic segmentation
https://github.com/michi-3000/eyeclip
공식 코드EyeCLIP: A visual-language foundation model for multi-modal ophthalmic image analysis
https://github.com/microsoft/ANCE
공식 코드Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
https://github.com/microsoft/CodeBERT
공식 코드UniXcoder: Unified Cross-Modal Pre-training for Code Representation
https://github.com/microsoft/DisentangledFaceGAN
공식 코드Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
https://github.com/microsoft/GLIP
공식 코드GLIPv2: Unifying Localization and Vision-Language Understanding
https://github.com/microsoft/LLM2CLIP
공식 코드LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation
https://github.com/microsoft/a-clip
공식 코드https://github.com/microsoft/ar2
공식 코드CodeRetriever: Unimodal and Bimodal Contrastive Learning for Code Search
https://github.com/microsoft/auto-formula
공식 코드https://github.com/microsoft/banknote-net
공식 코드BankNote-Net: Open dataset for assistive universal currency recognition
https://github.com/microsoft/binder
공식 코드Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning
https://github.com/microsoft/coco-lm
공식 코드COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
https://github.com/microsoft/figure
공식 코드FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations
https://github.com/microsoft/hi-ml/tree/main/hi-ml-multimodal
공식 코드Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing
https://github.com/microsoft/intrepid
공식 코드Towards Principled Representation Learning from Videos for Reinforcement Learning
https://github.com/microsoft/micon
공식 코드https://github.com/microsoft/react
공식 코드Learning Customized Visual Models with Retrieval-Augmented Knowledge
https://github.com/microsoft/robustlearn
공식 코드https://github.com/microsoft/satclip
공식 코드SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery
https://github.com/microsoft/unicl
공식 코드https://github.com/microsoft/wavtext5k
공식 코드https://github.com/microsoft/xpretrain
공식 코드Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning
https://github.com/mieskolainen/hypertrack
공식 코드https://github.com/mikomel/mlcl
공식 코드Multi-Label Contrastive Learning for Abstract Visual Reasoning
https://github.com/mimbres/neural-audio-fp
공식 코드Neural Audio Fingerprint for High-specific Audio Retrieval based on Contrastive Learning
https://github.com/minghchen/carl_code
공식 코드Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
https://github.com/mingkai-zheng/ReSSL
공식 코드Weak Augmentation Guided Relational Self-Supervised Learning
https://github.com/minogame/clip-mtob
공식 코드Design of the topology for contrastive visual-textual alignment
https://github.com/minttusofia/video_language_critic
공식 코드Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics
https://github.com/minwhoo/gacl
공식 코드https://github.com/mirthai/med3dvlm
공식 코드Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.