Picture for Matthew Brown

Matthew Brown

Module-wise Adaptive Distillation for Multimodality Foundation Models

Oct 06, 2023
Figure 1 for Module-wise Adaptive Distillation for Multimodality Foundation Models
Figure 2 for Module-wise Adaptive Distillation for Multimodality Foundation Models
Figure 3 for Module-wise Adaptive Distillation for Multimodality Foundation Models
Figure 4 for Module-wise Adaptive Distillation for Multimodality Foundation Models
Viaarxiv icon

Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text

Dec 14, 2021
Figure 1 for Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text
Figure 2 for Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text
Figure 3 for Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text
Figure 4 for Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text
Viaarxiv icon

Exploring Temporal Granularity in Self-Supervised Video Representation Learning

Add code
Dec 08, 2021
Figure 1 for Exploring Temporal Granularity in Self-Supervised Video Representation Learning
Figure 2 for Exploring Temporal Granularity in Self-Supervised Video Representation Learning
Figure 3 for Exploring Temporal Granularity in Self-Supervised Video Representation Learning
Figure 4 for Exploring Temporal Granularity in Self-Supervised Video Representation Learning
Viaarxiv icon

2.5D Visual Relationship Detection

Add code
Apr 26, 2021
Figure 1 for 2.5D Visual Relationship Detection
Figure 2 for 2.5D Visual Relationship Detection
Figure 3 for 2.5D Visual Relationship Detection
Figure 4 for 2.5D Visual Relationship Detection
Viaarxiv icon

MoViNets: Mobile Video Networks for Efficient Video Recognition

Add code
Apr 18, 2021
Figure 1 for MoViNets: Mobile Video Networks for Efficient Video Recognition
Figure 2 for MoViNets: Mobile Video Networks for Efficient Video Recognition
Figure 3 for MoViNets: Mobile Video Networks for Efficient Video Recognition
Figure 4 for MoViNets: Mobile Video Networks for Efficient Video Recognition
Viaarxiv icon

FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling

Add code
Apr 17, 2021
Figure 1 for FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling
Figure 2 for FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling
Figure 3 for FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling
Figure 4 for FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling
Viaarxiv icon

GeLaTO: Generative Latent Textured Objects

Add code
Aug 11, 2020
Figure 1 for GeLaTO: Generative Latent Textured Objects
Figure 2 for GeLaTO: Generative Latent Textured Objects
Figure 3 for GeLaTO: Generative Latent Textured Objects
Figure 4 for GeLaTO: Generative Latent Textured Objects
Viaarxiv icon

When Ensembling Smaller Models is More Efficient than Single Large Models

Add code
May 01, 2020
Figure 1 for When Ensembling Smaller Models is More Efficient than Single Large Models
Figure 2 for When Ensembling Smaller Models is More Efficient than Single Large Models
Figure 3 for When Ensembling Smaller Models is More Efficient than Single Large Models
Viaarxiv icon

Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective

Add code
Mar 24, 2020
Figure 1 for Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
Figure 2 for Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
Figure 3 for Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
Figure 4 for Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
Viaarxiv icon

Federated Visual Classification with Real-World Data Distribution

Add code
Mar 18, 2020
Figure 1 for Federated Visual Classification with Real-World Data Distribution
Figure 2 for Federated Visual Classification with Real-World Data Distribution
Figure 3 for Federated Visual Classification with Real-World Data Distribution
Figure 4 for Federated Visual Classification with Real-World Data Distribution
Viaarxiv icon