Picture for Yunpeng Chen

Yunpeng Chen

Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models

Add code
May 29, 2023
Figure 1 for Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
Figure 2 for Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
Figure 3 for Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
Figure 4 for Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
Viaarxiv icon

Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation

Add code
Mar 23, 2022
Figure 1 for Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation
Figure 2 for Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation
Figure 3 for Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation
Figure 4 for Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation
Viaarxiv icon

SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representations

Add code
Feb 15, 2022
Figure 1 for SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representations
Figure 2 for SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representations
Figure 3 for SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representations
Figure 4 for SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representations
Viaarxiv icon

MorphMLP: A Self-Attention Free, MLP-Like Backbone for Image and Video

Add code
Nov 24, 2021
Figure 1 for MorphMLP: A Self-Attention Free, MLP-Like Backbone for Image and Video
Figure 2 for MorphMLP: A Self-Attention Free, MLP-Like Backbone for Image and Video
Figure 3 for MorphMLP: A Self-Attention Free, MLP-Like Backbone for Image and Video
Figure 4 for MorphMLP: A Self-Attention Free, MLP-Like Backbone for Image and Video
Viaarxiv icon

Improved Pillar with Fine-grained Feature for 3D Object Detection

Add code
Oct 12, 2021
Figure 1 for Improved Pillar with Fine-grained Feature for 3D Object Detection
Figure 2 for Improved Pillar with Fine-grained Feature for 3D Object Detection
Figure 3 for Improved Pillar with Fine-grained Feature for 3D Object Detection
Figure 4 for Improved Pillar with Fine-grained Feature for 3D Object Detection
Viaarxiv icon

Dense Contrastive Visual-Linguistic Pretraining

Add code
Sep 24, 2021
Figure 1 for Dense Contrastive Visual-Linguistic Pretraining
Figure 2 for Dense Contrastive Visual-Linguistic Pretraining
Figure 3 for Dense Contrastive Visual-Linguistic Pretraining
Figure 4 for Dense Contrastive Visual-Linguistic Pretraining
Viaarxiv icon

PnP-DETR: Towards Efficient Visual Analysis with Transformers

Add code
Sep 16, 2021
Figure 1 for PnP-DETR: Towards Efficient Visual Analysis with Transformers
Figure 2 for PnP-DETR: Towards Efficient Visual Analysis with Transformers
Figure 3 for PnP-DETR: Towards Efficient Visual Analysis with Transformers
Figure 4 for PnP-DETR: Towards Efficient Visual Analysis with Transformers
Viaarxiv icon

Continual Learning via Bit-Level Information Preserving

Add code
May 10, 2021
Figure 1 for Continual Learning via Bit-Level Information Preserving
Figure 2 for Continual Learning via Bit-Level Information Preserving
Figure 3 for Continual Learning via Bit-Level Information Preserving
Figure 4 for Continual Learning via Bit-Level Information Preserving
Viaarxiv icon

Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

Add code
Jan 28, 2021
Figure 1 for Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Figure 2 for Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Figure 3 for Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Figure 4 for Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Viaarxiv icon

ProxylessKD: Direct Knowledge Distillation with Inherited Classifier for Face Recognition

Add code
Oct 31, 2020
Figure 1 for ProxylessKD: Direct Knowledge Distillation with Inherited Classifier for Face Recognition
Figure 2 for ProxylessKD: Direct Knowledge Distillation with Inherited Classifier for Face Recognition
Figure 3 for ProxylessKD: Direct Knowledge Distillation with Inherited Classifier for Face Recognition
Figure 4 for ProxylessKD: Direct Knowledge Distillation with Inherited Classifier for Face Recognition
Viaarxiv icon