Neil Houlsby

papers

9,272

total citations

papers (16)

Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts

NEURIPS 2022arXiv

286

citations

On Scaling Up a Multilingual Vision and Language Model

CVPR 2024arXiv

256

citations

Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

NEURIPS 2023arXiv

198

citations

On Robustness and Transferability of Convolutional Neural Networks

CVPR 2021arXiv

168

citations

Image Captioners Are Scalable Vision Learners Too

NEURIPS 2023arXiv

citations

UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes

NEURIPS 2022arXiv

citations

CLIPPO: Image-and-Language Understanding From Pixels Only

CVPR 2023arXiv

citations

Self-Supervised Learning of Video-Induced Visual Invariances

CVPR 2020arXiv

citations

Frozen Feature Augmentation for Few-Shot Image Classification

CVPR 2024arXiv

citations

Neil Houlsby

papers (16)

MLP-Mixer: An all-MLP Architecture for Vision

Scaling Vision Transformers

Big Transfer (BiT): General Visual Representation Learning

Scaling Vision with Sparse Mixture of Experts

Revisiting the Calibration of Modern Neural Networks

Simple Open-Vocabulary Object Detection with Vision Transformers

Scaling Open-Vocabulary Object Detection

Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts

On Scaling Up a Multilingual Vision and Language Model

Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

On Robustness and Transferability of Convolutional Neural Networks

Image Captioners Are Scalable Vision Learners Too

UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes

CLIPPO: Image-and-Language Understanding From Pixels Only

Self-Supervised Learning of Video-Induced Visual Invariances

Frozen Feature Augmentation for Few-Shot Image Classification

papers (16)

MLP-Mixer: An all-MLP Architecture for Vision

Scaling Vision Transformers

Big Transfer (BiT): General Visual Representation Learning

Scaling Vision with Sparse Mixture of Experts

Revisiting the Calibration of Modern Neural Networks

Simple Open-Vocabulary Object Detection with Vision Transformers

Scaling Open-Vocabulary Object Detection

Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts

On Scaling Up a Multilingual Vision and Language Model

Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

On Robustness and Transferability of Convolutional Neural Networks

Image Captioners Are Scalable Vision Learners Too

UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes

CLIPPO: Image-and-Language Understanding From Pixels Only

Self-Supervised Learning of Video-Induced Visual Invariances

Frozen Feature Augmentation for Few-Shot Image Classification