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 5026–5050 of 6661 papers

TitleStatusHype
Cross-Domain 3D Hand Pose Estimation With Dual Modalities—0
SGAligner: 3D Scene Alignment with Scene Graphs—0
CAP: Robust Point Cloud Classification via Semantic and Structural Modeling—0
HyperMatch: Noise-Tolerant Semi-Supervised Learning via Relaxed Contrastive Constraint—0
Speech4Mesh: Speech-Assisted Monocular 3D Facial Reconstruction for Speech-Driven 3D Facial Animation—0
Implicit Surface Contrastive Clustering for LiDAR Point Clouds—0
Contrastive Learning Relies More on Spatial Inductive Bias Than Supervised Learning: An Empirical Study—0
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One ClassifierCode0
Deep Temporal Contrastive Clustering—0
Truncate-Split-Contrast: A Framework for Learning from Mislabeled Videos—0
Precise Location Matching Improves Dense Contrastive Learning in Digital PathologyCode0
Multilingual News Location Detection using an Entity-Based Siamese Network with Semi-Supervised Contrastive Learning and Knowledge BaseCode0
Understanding and Improving the Role of Projection Head in Self-Supervised Learning—0
Restoring Vision in Hazy Weather with Hierarchical Contrastive Learning—0
Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval—0
ALCAP: Alignment-Augmented Music CaptionerCode0
MoQuad: Motion-focused Quadruple Construction for Video Contrastive Learning—0
Continual Contrastive Finetuning Improves Low-Resource Relation Extraction—0
Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document UnderstandingCode0
WACO: Word-Aligned Contrastive Learning for Speech TranslationCode0
Disentangling Learnable and Memorizable Data via Contrastive Learning for Semantic Communications—0
Hyperbolic Hierarchical Contrastive Hashing—0
TCFimt: Temporal Counterfactual Forecasting from Individual Multiple Treatment Perspective—0
CLIPPO: Image-and-Language Understanding from Pixels Only—0
Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders—0
Show:102550
← PrevPage 202 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