SOTAVerified

Contrastive Learning

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)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1651–1675 of 6661 papers

TitleStatusHype
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual RepresentationsCode1
Relative Contrastive Learning for Sequential Recommendation with Similarity-based Positive Pair SelectionCode1
Towards Cross-Table Masked Pretraining for Web Data MiningCode1
RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable DataCode1
A Simple and Effective Self-Supervised Contrastive Learning Framework for Aspect DetectionCode1
Representation Learning via Invariant Causal MechanismsCode1
Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic SegmentationCode1
ReSSL: Relational Self-Supervised Learning with Weak AugmentationCode1
CL4CTR: A Contrastive Learning Framework for CTR PredictionCode1
Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal PerspectiveCode1
CURL: Contrastive Unsupervised Representation Learning for Reinforcement LearningCode1
CURL: Contrastive Unsupervised Representations for Reinforcement LearningCode1
Efficient fine-tuning methodology of text embedding models for information retrieval: contrastive learning penalty (clp)Code1
Rethinking the Effect of Data Augmentation in Adversarial Contrastive LearningCode1
Efficient Contrastive Learning via Novel Data Augmentation and Curriculum LearningCode1
Retrieval Augmented Generation with Collaborative Filtering for Personalized Text GenerationCode1
CUTS: A Deep Learning and Topological Framework for Multigranular Unsupervised Medical Image SegmentationCode1
A Simple Contrastive Learning Objective for Alleviating Neural Text DegenerationCode1
Efficient Fourier Filtering Network with Contrastive Learning for UAV-based Unaligned Bi-modal Salient Object DetectionCode1
Efficient Vision-Language Pre-training by Cluster MaskingCode1
A simple, efficient and scalable contrastive masked autoencoder for learning visual representationsCode1
Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete TokensCode1
CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTsCode1
Effective Conditioned and Composed Image Retrieval Combining CLIP-Based FeaturesCode1
Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural NetworksCode1
Show:102550
← PrevPage 67 of 267Next →
All datasetsimagenet-1k10,000 People - Human Pose Recognition DataCIFAR-10STL-10

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6—Unverified
2ResNet50ImageNet Top-1 Accuracy73—Unverified
3ResNet50ImageNet Top-1 Accuracy71.1—Unverified
4ResNet50ImageNet Top-1 Accuracy69.3—Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6—Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8—Unverified
7ResNet50ImageNet Top-1 Accuracy63.6—Unverified
8ResNet50ImageNet Top-1 Accuracy61.5—Unverified
9ResNet50ImageNet Top-1 Accuracy61.5—Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3—Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1—Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77—Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55—Unverified