DINOv2: Learning Robust Visual Features without Supervision

Maxime Oquab, Timothée Darcet, Théo Moutakanni, +23

arXiv (Cornell University)

EngineeringMachine LearningRobust FeatureNatural Language ProcessingMultimodal Llm +17

ResMLP: Feedforward Networks for Image Classification With Data-Efficient Training

Hugo Touvron, Piotr Bojanowski, Mathilde Caron, +8

IEEE Transactions on Pattern Analysis and Machine Intelligence

Few-shot LearningConvolutional Neural NetworkEngineeringMachine LearningMultimodal Llm +17

ImageBind One Embedding Space to Bind Them All

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

XCiT: Cross-Covariance Image Transformers

Alaaeldin El-Nouby, Hugo Touvron, Mathilde Caron, +8

arXiv (Cornell University)

Convolutional Neural NetworkEngineeringMachine LearningMulti-image FusionNatural Language Processing +17

Training Vision Transformers for Image Retrieval

Alaaeldin El-Nouby, Natalia Neverova, Ivan Laptev, +1

arXiv (Cornell University)

Machine VisionImage AnalysisMachine LearningData ScienceImage Retrieval +11

LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference

Ben Graham, Alaaeldin El-Nouby, Hugo Touvron, +4

arXiv (Cornell University)

Convolutional Neural NetworkEngineeringMachine LearningImage ClassificationImage Analysis +15

OmniMAE: Single Model Masked Pretraining on Images and Videos

Rohit Girdhar, Alaaeldin El-Nouby, Mannat Singh, +3

Multiple Visual ModalitiesEngineeringMachine LearningTransformer-based ArchitecturesVideo Processing +14

Augmenting Convolutional networks with attention-based aggregation

Hugo Touvron, Matthieu Cord, Alaaeldin El-Nouby, +4

arXiv (Cornell University)

Data AugmentationConvolutional Neural NetworkMachine VisionMachine LearningData Science +13

Are Large-scale Datasets Necessary for Self-Supervised Pre-training?

Alaaeldin El-Nouby, Gautier Izacard, Hugo Touvron, +2

arXiv (Cornell University)

Few-shot LearningEngineeringMachine LearningAutoencodersImagenet Pre-training +18

Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction

Alaaeldin El-Nouby, Shikhar Sharma, Hannes Schulz, +5

Artificial IntelligenceFeedback HistoryEngineeringMachine LearningModifying Images +20