Picture for Boxiao Liu

Boxiao Liu

Enhancing Vision-Language Model with Unmasked Token Alignment

Add code
May 29, 2024
Viaarxiv icon

RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths

Add code
May 29, 2023
Figure 1 for RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths
Figure 2 for RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths
Figure 3 for RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths
Figure 4 for RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths
Viaarxiv icon

Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding

Mar 20, 2023
Figure 1 for Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding
Figure 2 for Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding
Figure 3 for Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding
Figure 4 for Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding
Viaarxiv icon

Rethinking Robust Representation Learning Under Fine-grained Noisy Faces

Aug 08, 2022
Figure 1 for Rethinking Robust Representation Learning Under Fine-grained Noisy Faces
Figure 2 for Rethinking Robust Representation Learning Under Fine-grained Noisy Faces
Figure 3 for Rethinking Robust Representation Learning Under Fine-grained Noisy Faces
Figure 4 for Rethinking Robust Representation Learning Under Fine-grained Noisy Faces
Viaarxiv icon

TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers

Add code
Jul 18, 2022
Figure 1 for TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers
Figure 2 for TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers
Figure 3 for TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers
Figure 4 for TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers
Viaarxiv icon

Meta Knowledge Distillation

Add code
Feb 16, 2022
Figure 1 for Meta Knowledge Distillation
Figure 2 for Meta Knowledge Distillation
Figure 3 for Meta Knowledge Distillation
Figure 4 for Meta Knowledge Distillation
Viaarxiv icon

An Efficient Pruning Process with Locality Aware Exploration and Dynamic Graph Editing for Subgraph Matching

Dec 22, 2021
Figure 1 for An Efficient Pruning Process with Locality Aware Exploration and Dynamic Graph Editing for Subgraph Matching
Figure 2 for An Efficient Pruning Process with Locality Aware Exploration and Dynamic Graph Editing for Subgraph Matching
Figure 3 for An Efficient Pruning Process with Locality Aware Exploration and Dynamic Graph Editing for Subgraph Matching
Figure 4 for An Efficient Pruning Process with Locality Aware Exploration and Dynamic Graph Editing for Subgraph Matching
Viaarxiv icon

FNAS: Uncertainty-Aware Fast Neural Architecture Search

Add code
May 27, 2021
Figure 1 for FNAS: Uncertainty-Aware Fast Neural Architecture Search
Figure 2 for FNAS: Uncertainty-Aware Fast Neural Architecture Search
Figure 3 for FNAS: Uncertainty-Aware Fast Neural Architecture Search
Figure 4 for FNAS: Uncertainty-Aware Fast Neural Architecture Search
Viaarxiv icon

Utilizing the Instability in Weakly Supervised Object Detection

Jun 14, 2019
Figure 1 for Utilizing the Instability in Weakly Supervised Object Detection
Figure 2 for Utilizing the Instability in Weakly Supervised Object Detection
Figure 3 for Utilizing the Instability in Weakly Supervised Object Detection
Figure 4 for Utilizing the Instability in Weakly Supervised Object Detection
Viaarxiv icon