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 1651–1700 of 6661 papers

TitleStatusHype
COT: A Generative Approach for Hate Speech Counter-Narratives via Contrastive Optimal Transport—0
Effective Generation of Feasible Solutions for Integer Programming via Guided DiffusionCode0
Spatially Resolved Gene Expression Prediction from Histology via Multi-view Graph Contrastive Learning with HSIC-bottleneck Regularization—0
Self-Supervised Time-Series Anomaly Detection Using Learnable Data Augmentation—0
RIGL: A Unified Reciprocal Approach for Tracing the Independent and Group Learning ProcessesCode0
GroPrompt: Efficient Grounded Prompting and Adaptation for Referring Video Object Segmentation—0
BIOSCAN-5M: A Multimodal Dataset for Insect BiodiversityCode1
Toward Exploring the Code Understanding Capabilities of Pre-trained Code Generation Models—0
InternalInspector I^2: Robust Confidence Estimation in LLMs through Internal States—0
Balancing Embedding Spectrum for RecommendationCode0
UniGLM: Training One Unified Language Model for Text-Attributed Graph EmbeddingCode1
Can Machines Resonate with Humans? Evaluating the Emotional and Empathic Comprehension of LMsCode0
Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion ModelsCode1
DiffMM: Multi-Modal Diffusion Model for RecommendationCode2
GAugLLM: Improving Graph Contrastive Learning for Text-Attributed Graphs with Large Language ModelsCode1
Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding—0
Mix-Domain Contrastive Learning for Unpaired H&E-to-IHC Stain TranslationCode0
On the Effectiveness of Supervision in Asymmetric Non-Contrastive LearningCode0
SparseCL: Sparse Contrastive Learning for Contradiction Retrieval—0
SemanticMIM: Marring Masked Image Modeling with Semantics Compression for General Visual RepresentationCode0
Self-Supervised Representation Learning with Spatial-Temporal Consistency for Sign Language RecognitionCode1
Shelf-Supervised Cross-Modal Pre-Training for 3D Object DetectionCode0
Pcc-tuning: Breaking the Contrastive Learning Ceiling in Semantic Textual SimilarityCode0
Fine-Grained Urban Flow Inference with Multi-scale Representation Learning—0
T-JEPA: A Joint-Embedding Predictive Architecture for Trajectory Similarity Computation—0
Modeling Comparative Logical Relation with Contrastive Learning for Text Generation—0
An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image RetrievalCode2
Federated Contrastive Learning for Personalized Semantic Communication—0
CLDTA: Contrastive Learning based on Diagonal Transformer Autoencoder for Cross-Dataset EEG Emotion Recognition—0
SCDNet: Self-supervised Learning Feature-based Speaker Change Detection—0
Languages Transferred Within the Encoder: On Representation Transfer in Zero-Shot Multilingual TranslationCode0
Label-aware Hard Negative Sampling Strategies with Momentum Contrastive Learning for Implicit Hate Speech DetectionCode0
Exploring Self-Supervised Multi-view Contrastive Learning for Speech Emotion Recognition with Limited Annotations—0
Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression LearningCode2
Training Dynamics of Nonlinear Contrastive Learning Model in the High Dimensional Limit—0
Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?—0
Joint Learning of Context and Feedback Embeddings in Spoken Dialogue—0
Learning Domain-Invariant Features for Out-of-Context News Detection—0
Rethinking the impact of noisy labels in graph classification: A utility and privacy perspective—0
Benchmarking Vision-Language Contrastive Methods for Medical Representation LearningCode0
SSCL-IDS: Enhancing Generalization of Intrusion Detection with Self-Supervised Contrastive LearningCode0
Weighted KL-Divergence for Document Ranking Model Refinement—0
Contrastive learning of T cell receptor representationsCode0
NeuroMoCo: A Neuromorphic Momentum Contrast Learning Method for Spiking Neural Networks—0
Text-aware and Context-aware Expressive Audiobook Speech Synthesis—0
PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive LearningCode0
Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and LanguageCode2
Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World AttacksCode1
Anomaly Multi-classification in Industrial Scenarios: Transferring Few-shot Learning to a New TaskCode0
Deep Learning to Predict Glaucoma Progression using Structural Changes in the Eye—0
Show:102550
← PrevPage 34 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