Picture for Yuxin Fang

Yuxin Fang

EVA-CLIP: Improved Training Techniques for CLIP at Scale

Add code
Mar 27, 2023
Figure 1 for EVA-CLIP: Improved Training Techniques for CLIP at Scale
Figure 2 for EVA-CLIP: Improved Training Techniques for CLIP at Scale
Figure 3 for EVA-CLIP: Improved Training Techniques for CLIP at Scale
Figure 4 for EVA-CLIP: Improved Training Techniques for CLIP at Scale
Viaarxiv icon

EVA-02: A Visual Representation for Neon Genesis

Add code
Mar 22, 2023
Figure 1 for EVA-02: A Visual Representation for Neon Genesis
Figure 2 for EVA-02: A Visual Representation for Neon Genesis
Figure 3 for EVA-02: A Visual Representation for Neon Genesis
Figure 4 for EVA-02: A Visual Representation for Neon Genesis
Viaarxiv icon

EVA: Exploring the Limits of Masked Visual Representation Learning at Scale

Add code
Nov 14, 2022
Figure 1 for EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
Figure 2 for EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
Figure 3 for EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
Figure 4 for EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
Viaarxiv icon

Temporally Efficient Vision Transformer for Video Instance Segmentation

Add code
Apr 18, 2022
Figure 1 for Temporally Efficient Vision Transformer for Video Instance Segmentation
Figure 2 for Temporally Efficient Vision Transformer for Video Instance Segmentation
Figure 3 for Temporally Efficient Vision Transformer for Video Instance Segmentation
Figure 4 for Temporally Efficient Vision Transformer for Video Instance Segmentation
Viaarxiv icon

Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection

Add code
Apr 06, 2022
Figure 1 for Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection
Figure 2 for Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection
Figure 3 for Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection
Figure 4 for Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection
Viaarxiv icon

Corrupted Image Modeling for Self-Supervised Visual Pre-Training

Add code
Feb 07, 2022
Figure 1 for Corrupted Image Modeling for Self-Supervised Visual Pre-Training
Figure 2 for Corrupted Image Modeling for Self-Supervised Visual Pre-Training
Figure 3 for Corrupted Image Modeling for Self-Supervised Visual Pre-Training
Figure 4 for Corrupted Image Modeling for Self-Supervised Visual Pre-Training
Viaarxiv icon

What Makes for Hierarchical Vision Transformer?

Add code
Jul 05, 2021
Figure 1 for What Makes for Hierarchical Vision Transformer?
Figure 2 for What Makes for Hierarchical Vision Transformer?
Figure 3 for What Makes for Hierarchical Vision Transformer?
Figure 4 for What Makes for Hierarchical Vision Transformer?
Viaarxiv icon

Tracking Instances as Queries

Add code
Jun 23, 2021
Figure 1 for Tracking Instances as Queries
Figure 2 for Tracking Instances as Queries
Figure 3 for Tracking Instances as Queries
Figure 4 for Tracking Instances as Queries
Viaarxiv icon

You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection

Add code
Jun 21, 2021
Figure 1 for You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
Figure 2 for You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
Figure 3 for You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
Figure 4 for You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
Viaarxiv icon

Instances as Queries

Add code
May 23, 2021
Figure 1 for Instances as Queries
Figure 2 for Instances as Queries
Figure 3 for Instances as Queries
Figure 4 for Instances as Queries
Viaarxiv icon