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 3501–3525 of 6661 papers

TitleStatusHype
Weakly-Supervised Text Instance Segmentation—0
Weakly-Supervised Video Object Grounding via Causal Intervention—0
Weak Supervision for Real World Graphs—0
Weak Supervision with Arbitrary Single Frame for Micro- and Macro-expression Spotting—0
Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection—0
WebGuard++:Interpretable Malicious URL Detection via Bidirectional Fusion of HTML Subgraphs and Multi-Scale Convolutional BERT—0
WeedCLR: Weed Contrastive Learning through Visual Representations with Class-Optimized Loss in Long-Tailed Datasets—0
Weighted KL-Divergence for Document Ranking Model Refinement—0
Weighted Point Cloud Normal Estimation—0
What About Taking Policy as Input of Value Function: Policy-extended Value Function Approximator—0
Uncovering the Over-smoothing Challenge in Image Super-Resolution: Entropy-based Quantification and Contrastive Optimization—0
What Makes for Good Representations for Contrastive Learning—0
What Makes for Good Views for Contrastive Learning?—0
What Remains of Visual Semantic Embeddings—0
What Should Not Be Contrastive in Contrastive Learning—0
Finding Shared Decodable Concepts and their Negations in the Brain—0
What Time Tells Us? An Explorative Study of Time Awareness Learned from Static Images—0
What to align in multimodal contrastive learning?—0
When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?—0
When does CLIP generalize better than unimodal models? When judging human-centric concepts—0
When Does Contrastive Visual Representation Learning Work?—0
When Graph Contrastive Learning Backfires: Spectral Vulnerability and Defense in Recommendation—0
When hard negative sampling meets supervised contrastive learning—0
Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression—0
WildSAT: Learning Satellite Image Representations from Wildlife Observations—0
Show:102550
← PrevPage 141 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