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 5151–5200 of 6661 papers

TitleStatusHype
Uncertainty-aware Contrastive Distillation for Incremental Semantic SegmentationCode1
Improving Contrastive Learning with Model AugmentationCode1
Multi-scale and Cross-scale Contrastive Learning for Semantic SegmentationCode1
Unsupervised Pre-training for Temporal Action Localization TasksCode1
Self-Supervised Predictive Learning: A Negative-Free Method for Sound Source Localization in Visual ScenesCode1
Versatile Multi-Modal Pre-Training for Human-Centric PerceptionCode1
Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic SegmentationCode2
Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation OverlapCode1
A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training—0
Probing Representation Forgetting in Supervised and Unsupervised Continual Learning—0
On Understanding and Mitigating the Dimensional Collapse of Graph Contrastive Learning: a Non-Maximum Removal Approach—0
Learning Hierarchical Cross-Modal Association for Co-Speech Gesture GenerationCode1
Tackling Online One-Class Incremental Learning by Removing Negative Contrasts—0
Self-supervised Video-centralised Transformer for Video Face Clustering—0
mcBERT: Momentum Contrastive Learning with BERT for Zero-Shot Slot Filling—0
Steganalysis of Image with Adaptively Parametric Activation—0
Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image TranslationCode1
R3M: A Universal Visual Representation for Robot ManipulationCode2
Negative Selection by Clustering for Contrastive Learning in Human Activity Recognition—0
Text Transformations in Contrastive Self-Supervised Learning: A Review—0
Towards Textual Out-of-Domain Detection without In-Domain Labels—0
Utterance Rewriting with Contrastive Learning in Multi-turn Dialogue—0
Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition—0
CP2: Copy-Paste Contrastive Pretraining for Semantic SegmentationCode1
Unsupervised Deraining: Where Contrastive Learning Meets Self-similarityCode1
Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL—0
Language modeling via stochastic processesCode1
Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency PerspectiveCode1
Partitioning Image Representation in Contrastive Learning—0
SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware NormalizationCode1
Multi-view Multi-behavior Contrastive Learning in RecommendationCode1
Prototypical Verbalizer for Prompt-based Few-shot TuningCode4
Contrastive Learning with Positive-Negative Frame Mask for Music Representation—0
Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time SeriesCode1
CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in SegmentationCode0
Modulated Contrast for Versatile Image SynthesisCode1
PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation—0
Contrastive Learning for Cross-Domain Open World RecognitionCode1
Robustness through Cognitive Dissociation Mitigation in Contrastive Adversarial TrainingCode0
Weak Augmentation Guided Relational Self-Supervised LearningCode1
QS-Attn: Query-Selected Attention for Contrastive Learning in I2I TranslationCode1
Is it all a cluster game? -- Exploring Out-of-Distribution Detection based on Clustering in the Embedding Space—0
Multi-View Dreaming: Multi-View World Model with Contrastive Learning—0
Better Quality Estimation for Low Resource Corpus Mining—0
Improving Word Translation via Two-Stage Contrastive LearningCode1
InsCon:Instance Consistency Feature Representation via Self-Supervised Learning—0
Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning—0
Contrastive Learning of Sociopragmatic Meaning in Social MediaCode0
Supervised Contrastive Learning with Structure Inference for Graph Classification—0
Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little CostCode1
Show:102550
← PrevPage 104 of 134Next →
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