Picture for Xiaodan Liang

Xiaodan Liang

Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

Add code
Sep 06, 2021
Figure 1 for Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection
Figure 2 for Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection
Figure 3 for Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection
Figure 4 for Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection
Viaarxiv icon

Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift

Add code
Aug 22, 2021
Figure 1 for Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift
Figure 2 for Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift
Figure 3 for Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift
Figure 4 for Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift
Viaarxiv icon

Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning

Add code
Aug 18, 2021
Figure 1 for Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning
Figure 2 for Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning
Figure 3 for Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning
Figure 4 for Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning
Viaarxiv icon

M3D-VTON: A Monocular-to-3D Virtual Try-On Network

Add code
Aug 11, 2021
Figure 1 for M3D-VTON: A Monocular-to-3D Virtual Try-On Network
Figure 2 for M3D-VTON: A Monocular-to-3D Virtual Try-On Network
Figure 3 for M3D-VTON: A Monocular-to-3D Virtual Try-On Network
Figure 4 for M3D-VTON: A Monocular-to-3D Virtual Try-On Network
Viaarxiv icon

Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining

Add code
Aug 09, 2021
Figure 1 for Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining
Figure 2 for Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining
Figure 3 for Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining
Figure 4 for Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining
Viaarxiv icon

NASOA: Towards Faster Task-oriented Online Fine-tuning with a Zoo of Models

Add code
Aug 07, 2021
Figure 1 for NASOA: Towards Faster Task-oriented Online Fine-tuning with a Zoo of Models
Figure 2 for NASOA: Towards Faster Task-oriented Online Fine-tuning with a Zoo of Models
Figure 3 for NASOA: Towards Faster Task-oriented Online Fine-tuning with a Zoo of Models
Figure 4 for NASOA: Towards Faster Task-oriented Online Fine-tuning with a Zoo of Models
Viaarxiv icon

WAS-VTON: Warping Architecture Search for Virtual Try-on Network

Add code
Aug 01, 2021
Figure 1 for WAS-VTON: Warping Architecture Search for Virtual Try-on Network
Figure 2 for WAS-VTON: Warping Architecture Search for Virtual Try-on Network
Figure 3 for WAS-VTON: Warping Architecture Search for Virtual Try-on Network
Figure 4 for WAS-VTON: Warping Architecture Search for Virtual Try-on Network
Viaarxiv icon

Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation

Add code
Jul 23, 2021
Figure 1 for Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation
Figure 2 for Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation
Figure 3 for Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation
Figure 4 for Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation
Viaarxiv icon

Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation

Add code
Jul 23, 2021
Figure 1 for Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation
Figure 2 for Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation
Figure 3 for Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation
Figure 4 for Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation
Viaarxiv icon

AutoBERT-Zero: Evolving BERT Backbone from Scratch

Add code
Jul 15, 2021
Figure 1 for AutoBERT-Zero: Evolving BERT Backbone from Scratch
Figure 2 for AutoBERT-Zero: Evolving BERT Backbone from Scratch
Figure 3 for AutoBERT-Zero: Evolving BERT Backbone from Scratch
Figure 4 for AutoBERT-Zero: Evolving BERT Backbone from Scratch
Viaarxiv icon