Emerging Properties in Self-Supervised Vision Transformers

Mathilde Caron, Hugo Touvron, Ishan Misra, +4

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Self-supervised Vit FeaturesImage ClassificationConvolutional Neural NetworkImage AnalysisMachine Vision +13

Unsupervised Learning of Visual Features by Contrasting Cluster Assignments

Mathilde Caron, Ishan Misra, Julien Mairal, +3

arXiv (Cornell University)

EngineeringMachine LearningUnsupervised Machine LearningImage AnalysisData Science +16

DINOv2: Learning Robust Visual Features without Supervision

Maxime Oquab, Timothée Darcet, Théo Moutakanni, +23

arXiv (Cornell University)

EngineeringMachine LearningRobust FeatureNatural Language ProcessingMultimodal Llm +17

Barlow Twins: Self-Supervised Learning via Redundancy Reduction

Jure Žbontar, Jing Li, Ishan Misra, +2

arXiv (Cornell University)

Network TwinsConvolutional Neural NetworkEngineeringMachine LearningImage Analysis +14

MDETR - Modulated Detection for End-to-End Multi-Modal Understanding

Aishwarya Kamath, Mannat Singh, Yann LeCun, +3

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

EngineeringMachine LearningObject DetectorPhrase GroundingMultimodal Learning +21

ImageBind One Embedding Space to Bind Them All

Rohit Girdhar, Alaaeldin El-Nouby, Zhuang Liu, +4

In Defense of Grid Features for Visual Question Answering

Huaizu Jiang, Ishan Misra, Marcus Rohrbach, +2

Natural Language ProcessingMultimodal LlmMachine VisionImage AnalysisData Science +13

Self-Supervised Pretraining of 3D Features on any Point-Cloud

Zaiwei Zhang, Rohit Girdhar, Armand Joulin, +1

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

EngineeringMachine LearningPoint Cloud ProcessingPoint Cloud3D Computer Vision +18

Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

Mahmoud Assran, Quentin Duval, Ishan Misra, +5

Convolutional Neural NetworkEngineeringMachine LearningDepth PredictionVision Transformers +15

From Red Wine to Red Tomato: Composition with Context

Ishan Misra, Abhinav Gupta, Martial Hebert

Structured PredictionEngineeringMachine LearningComposition ApproachSemantics +16