Contrastive Learning
2165 papers with code • 1 benchmarks • 11 datasets
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.
(Image credit: Schroff et al. 2015)
Libraries
Use these libraries to find Contrastive Learning models and implementationsDatasets
Latest papers
InfoMatch: Entropy Neural Estimation for Semi-Supervised Image Classification
Semi-supervised image classification, leveraging pseudo supervision and consistency regularization, has demonstrated remarkable success.
Vision-and-Language Navigation via Causal Learning
In the pursuit of robust and generalizable environment perception and language understanding, the ubiquitous challenge of dataset bias continues to plague vision-and-language navigation (VLN) agents, hindering their performance in unseen environments.
MyGO: Discrete Modality Information as Fine-Grained Tokens for Multi-modal Knowledge Graph Completion
To overcome their inherent incompleteness, multi-modal knowledge graph completion (MMKGC) aims to discover unobserved knowledge from given MMKGs, leveraging both structural information from the triples and multi-modal information of the entities.
UniSAR: Modeling User Transition Behaviors between Search and Recommendation
In this paper, we propose a framework named UniSAR that effectively models the different types of fine-grained behavior transitions for providing users a Unified Search And Recommendation service.
WB LUTs: Contrastive Learning for White Balancing Lookup Tables
Automatic white balancing (AWB), one of the first steps in an integrated signal processing (ISP) pipeline, aims to correct the color cast induced by the scene illuminant.
An Experimental Comparison Of Multi-view Self-supervised Methods For Music Tagging
In this study, we expand the scope of pretext tasks applied to music by investigating and comparing the performance of new self-supervised methods for music tagging.
Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class Discovery
To counteract this inefficiency, we opt to cluster only the unlabelled instances and subsequently expand the cluster prototypes with our introduced potential prototypes to fast explore novel classes.
Latent Guard: a Safety Framework for Text-to-image Generation
Hence, we propose Latent Guard, a framework designed to improve safety measures in text-to-image generation.
Contrastive-Based Deep Embeddings for Label Noise-Resilient Histopathology Image Classification
Recent advancements in deep learning have proven highly effective in medical image classification, notably within histopathology.
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
We outperform encoder-only models by a large margin on word-level tasks and reach a new unsupervised state-of-the-art performance on the Massive Text Embeddings Benchmark (MTEB).