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

Showing 40764100 of 6661 papers

TitleStatusHype
Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised LearningCode1
CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive LearningCode1
Contrastive Learning Reduces Hallucination in ConversationsCode1
WACO: Word-Aligned Contrastive Learning for Speech TranslationCode0
Query-as-context Pre-training for Dense Passage RetrievalCode1
Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document UnderstandingCode0
Disentangling Learnable and Memorizable Data via Contrastive Learning for Semantic Communications0
On Isotropy, Contextualization and Learning Dynamics of Contrastive-based Sentence Representation LearningCode1
Hyperbolic Hierarchical Contrastive Hashing0
TCFimt: Temporal Counterfactual Forecasting from Individual Multiple Treatment Perspective0
Attentive Mask CLIPCode1
MAViL: Masked Audio-Video LearnersCode1
NeRF-Art: Text-Driven Neural Radiance Fields StylizationCode1
CLIPPO: Image-and-Language Understanding from Pixels Only0
Establishing a stronger baseline for lightweight contrastive modelsCode0
MA-GCL: Model Augmentation Tricks for Graph Contrastive LearningCode1
Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders0
Understanding Zero-Shot Adversarial Robustness for Large-Scale ModelsCode1
Mitigating Negative Style Transfer in Hybrid Dialogue SystemCode0
Tailoring Visual Object Representations to Human Requirements: A Case Study with a Recycling RobotCode0
Generative artificial intelligence-enabled dynamic detection of nicotine-related circuits0
A Machine Learning Enhanced Approach for Automated Sunquake Detection in Acoustic Emission Maps0
Boosting Semi-Supervised Learning with Contrastive Complementary Labeling0
On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive LearningCode1
Coarse-to-Fine Contrastive Learning on Graphs0
Show:102550
← PrevPage 164 of 267Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6Unverified
2ResNet50ImageNet Top-1 Accuracy73Unverified
3ResNet50ImageNet Top-1 Accuracy71.1Unverified
4ResNet50ImageNet Top-1 Accuracy69.3Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8Unverified
7ResNet50ImageNet Top-1 Accuracy63.6Unverified
8ResNet50ImageNet Top-1 Accuracy61.5Unverified
9ResNet50ImageNet Top-1 Accuracy61.5Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55Unverified