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 151–175 of 6661 papers

TitleStatusHype
Domain and Task-Focused Example Selection for Data-Efficient Contrastive Medical Image SegmentationCode0
An Interpretable Representation Learning Approach for Diffusion Tensor Imaging—0
AmorLIP: Efficient Language-Image Pretraining via AmortizationCode0
WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and SegmentationCode0
Manifold-aware Representation Learning for Degradation-agnostic Image Restoration—0
Grounding Bodily Awareness in Visual Representations for Efficient Policy LearningCode0
Rethinking Contrastive Learning in Graph Anomaly Detection: A Clean-View Perspective—0
Supervised Graph Contrastive Learning for Gene Regulatory Network—0
Structure-Aligned Protein Language ModelCode2
REOBench: Benchmarking Robustness of Earth Observation Foundation ModelsCode1
CoTSRF: Utilize Chain of Thought as Stealthy and Robust Fingerprint of Large Language Models—0
Learning Genomic Structure from k-mers—0
Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives—0
Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language ModelsCode0
Contrastive Learning-Enhanced Trajectory Matching for Small-Scale Dataset Distillation—0
TCSinger 2: Customizable Multilingual Zero-shot Singing Voice SynthesisCode2
Unsupervised Graph Clustering with Deep Structural EntropyCode0
FAID: Fine-grained AI-generated Text Detection using Multi-task Auxiliary and Multi-level Contrastive LearningCode0
Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents—0
Unify Graph Learning with Text: Unleashing LLM Potentials for Session Search—0
Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning—0
Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives—0
Towards Generating Realistic Underwater Images—0
Adapting Pretrained Language Models for Citation Classification via Self-Supervised Contrastive LearningCode0
Unveil Multi-Picture Descriptions for Multilingual Mild Cognitive Impairment Detection via Contrastive Learning—0
Show:102550
← PrevPage 7 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