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 426–450 of 6661 papers

TitleStatusHype
Implicit Contrastive Representation Learning with Guided Stop-gradientCode0
MaRI: Material Retrieval Integration across Domains—0
Aligning Text to Image in Diffusion Models is Easier Than You ThinkCode1
Contrastive Speaker-Aware Learning for Multi-party Dialogue Generation with LLMs—0
Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?—0
Towards Spatial Transcriptomics-guided Pathological Image Recognition with Batch-Agnostic EncoderCode0
Just Functioning as a Hook for Two-Stage Referring Multi-Object Tracking—0
Anatomy-Aware Conditional Image-Text Retrieval—0
TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion ModelsCode1
PersonaBooth: Personalized Text-to-Motion Generation—0
NukesFormers: Unpaired Hyperspectral Image Generation with Non-Uniform Domain Alignment—0
Cross-Lingual IPA Contrastive Learning for Zero-Shot NER—0
CLICv2: Image Complexity Representation via Content Invariance Contrastive Learning—0
DynamicID: Zero-Shot Multi-ID Image Personalization with Flexible Facial Editability—0
Heterogeneous bimodal attention fusion for speech emotion recognition—0
Towards Universal Text-driven CT Image SegmentationCode0
Removing Geometric Bias in One-Class Anomaly Detection with Adaptive Feature PerturbationCode0
Pretext Task Adversarial Learning for Unpaired Low-field to Ultra High-field MRI SynthesisCode0
Discrete Contrastive Learning for Diffusion Policies in Autonomous Driving—0
Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation—0
Frequency-Based Alignment of EEG and Audio Signals Using Contrastive Learning and SincNet for Auditory Attention DetectionCode1
Joint Masked Reconstruction and Contrastive Learning for Mining Interactions Between ProteinsCode0
Cross-modal Causal Relation Alignment for Video Question GroundingCode1
Variance-Aware Loss Scheduling for Multimodal Alignment in Low-Data Settings—0
External Reliable Information-enhanced Multimodal Contrastive Learning for Fake News Detection—0
Show:102550
← PrevPage 18 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