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 1–25 of 6661 papers

TitleStatusHype
HapticCap: A Multimodal Dataset and Task for Understanding User Experience of Vibration Haptic Signals—0
SGCL: Unifying Self-Supervised and Supervised Learning for Graph Recommendation—0
Overview of the TalentCLEF 2025: Skill and Job Title Intelligence for Human Capital Management—0
SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts—0
Similarity-Guided Diffusion for Contrastive Sequential Recommendation—0
Latent Space Consistency for Sparse-View CT Reconstruction—0
LLM-Driven Dual-Level Multi-Interest Modeling for Recommendation—0
Self-supervised pretraining of vision transformers for animal behavioral analysis and neural encoding—0
RadiomicsRetrieval: A Customizable Framework for Medical Image Retrieval Using Radiomics FeaturesCode1
When Graph Contrastive Learning Backfires: Spectral Vulnerability and Defense in Recommendation—0
NLGCL: Naturally Existing Neighbor Layers Graph Contrastive Learning for RecommendationCode1
Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-Semantic Embeddings—0
From ID-based to ID-free: Rethinking ID Effectiveness in Multimodal Collaborative Filtering RecommendationCode0
DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation—0
CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized CaptionsCode0
Hierarchical Interaction Summarization and Contrastive Prompting for Explainable Recommendations—0
Hierarchical Intent-guided Optimization with Pluggable LLM-Driven Semantics for Session-based RecommendationCode0
Neural-Driven Image EditingCode2
Helping CLIP See Both the Forest and the Trees: A Decomposition and Description Approach—0
Weakly-supervised Contrastive Learning with Quantity Prompts for Moving Infrared Small Target DetectionCode0
DARTS: A Dual-View Attack Framework for Targeted Manipulation in Federated Sequential Recommendation—0
Why Multi-Interest Fairness Matters: Hypergraph Contrastive Multi-Interest Learning for Fair Conversational Recommender SystemCode0
FOCUS: Fine-grained Optimization with Semantic Guided Understanding for Pedestrian Attributes Recognition—0
AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated TextCode0
DiMPLe -- Disentangled Multi-Modal Prompt Learning: Enhancing Out-Of-Distribution Alignment with Invariant and Spurious Feature Separation—0
Show:102550
← PrevPage 1 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