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 151–200 of 6661 papers

TitleStatusHype
An Interpretable Representation Learning Approach for Diffusion Tensor Imaging—0
Domain and Task-Focused Example Selection for Data-Efficient Contrastive Medical Image SegmentationCode0
AmorLIP: Efficient Language-Image Pretraining via AmortizationCode0
WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and SegmentationCode0
Manifold-aware Representation Learning for Degradation-agnostic Image Restoration—0
Grounding Bodily Awareness in Visual Representations for Efficient Policy LearningCode0
Rethinking Contrastive Learning in Graph Anomaly Detection: A Clean-View Perspective—0
Supervised Graph Contrastive Learning for Gene Regulatory Network—0
Structure-Aligned Protein Language ModelCode2
REOBench: Benchmarking Robustness of Earth Observation Foundation ModelsCode1
Learning Genomic Structure from k-mers—0
CoTSRF: Utilize Chain of Thought as Stealthy and Robust Fingerprint of Large Language Models—0
Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives—0
Contrastive Learning-Enhanced Trajectory Matching for Small-Scale Dataset Distillation—0
Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language ModelsCode0
TCSinger 2: Customizable Multilingual Zero-shot Singing Voice SynthesisCode2
Unsupervised Graph Clustering with Deep Structural EntropyCode0
Towards Generating Realistic Underwater Images—0
Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents—0
Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning—0
Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives—0
FAID: Fine-grained AI-generated Text Detection using Multi-task Auxiliary and Multi-level Contrastive LearningCode0
Adapting Pretrained Language Models for Citation Classification via Self-Supervised Contrastive LearningCode0
Unify Graph Learning with Text: Unleashing LLM Potentials for Session Search—0
Unveil Multi-Picture Descriptions for Multilingual Mild Cognitive Impairment Detection via Contrastive Learning—0
Self-Reinforced Graph Contrastive LearningCode0
Sat2Sound: A Unified Framework for Zero-Shot Soundscape Mapping—0
GMM-Based Comprehensive Feature Extraction and Relative Distance Preservation For Few-Shot Cross-Modal Retrieval—0
SPKLIP: Aligning Spike Video Streams with Natural Language—0
The Computation of Generalized Embeddings for Underwater Acoustic Target Recognition using Contrastive LearningCode0
Multiscale Adaptive Conflict-Balancing Model For Multimedia Deepfake Detection—0
Representation of perceived prosodic similarity of conversational feedback—0
LLM-CoT Enhanced Graph Neural Recommendation with Harmonized Group Policy Optimization—0
Multi-modal contrastive learning adapts to intrinsic dimensions of shared latent variables—0
Bridging Generative and Discriminative Learning: Few-Shot Relation Extraction via Two-Stage Knowledge-Guided Pre-trainingCode0
Contrastive Alignment with Semantic Gap-Aware Corrections in Text-Video RetrievalCode0
Not All Documents Are What You Need for Extracting Instruction Tuning Data—0
ViEEG: Hierarchical Neural Coding with Cross-Modal Progressive Enhancement for EEG-Based Visual Decoding—0
Fine-Grained ECG-Text Contrastive Learning via Waveform Understanding Enhancement—0
Towards Sustainability in 6G Network Slicing with Energy-Saving and Optimization Methods—0
Robust Cross-View Geo-Localization via Content-Viewpoint Disentanglement—0
DC-Seg: Disentangled Contrastive Learning for Brain Tumor Segmentation with Missing ModalitiesCode1
CellCLIP -- Learning Perturbation Effects in Cell Painting via Text-Guided Contrastive Learning—0
Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch MiningCode1
Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought CorrectionCode2
SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought ReasoningCode2
Fractal Graph Contrastive Learning—0
MoCLIP: Motion-Aware Fine-Tuning and Distillation of CLIP for Human Motion Generation—0
Less is More: Multimodal Region Representation via Pairwise Inter-view LearningCode0
FRET: Feature Redundancy Elimination for Test Time Adaptation—0
Show:102550
← PrevPage 4 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