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 6451–6475 of 6661 papers

TitleStatusHype
Self-supervised SAR-optical Data Fusion and Land-cover Mapping using Sentinel-1/-2 Images—0
Shot Contrastive Self-Supervised Learning for Scene Boundary Detection—0
Should we pre-train a decoder in contrastive learning for dense prediction tasks?—0
Shuffle & Divide: Contrastive Learning for Long Text—0
SHYI: Action Support for Contrastive Learning in High-Fidelity Text-to-Image Generation—0
Siamese Prototypical Contrastive Learning—0
SI-FID: Only One Objective Indicator for Evaluating Stitched Images—0
SigCLR: Sigmoid Contrastive Learning of Visual Representations—0
Signed Directed Graph Contrastive Learning with Laplacian Augmentation—0
Sign-Guided Bipartite Graph Hashing for Hamming Space Search—0
Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders—0
SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning—0
SILC: Improving Vision Language Pretraining with Self-Distillation—0
Sim2Real Object-Centric Keypoint Detection and Description—0
SimCGNN: Simple Contrastive Graph Neural Network for Session-based Recommendation—0
SimCLAD: A Simple Framework for Contrastive Learning of Acronym Disambiguation—0
Generalizing similarity in noisy setups: the DIBS phenomenon—0
Similarity-aware Positive Instance Sampling for Graph Contrastive Pre-training—0
Pairwise Supervision Can Provably Elicit a Decision Boundary—0
Similarity-Guided Diffusion for Contrastive Sequential Recommendation—0
SimMER: Simple Maximization of Entropy and Rank for Self-supervised Representation Learning—0
SimO Loss: Anchor-Free Contrastive Loss for Fine-Grained Supervised Contrastive Learning—0
Simple Contrastive Graph Clustering—0
Simple Contrastive Representation Adversarial Learning for NLP Tasks—0
Simple-Sampling and Hard-Mixup with Prototypes to Rebalance Contrastive Learning for Text Classification—0
Show:102550
← PrevPage 259 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