Xiaodan Liang

Linguistically Driven Graph Capsule Network for Visual Question Reasoning

Mar 23, 2020
Qingxing Cao, Xiaodan Liang, Keze Wang, Liang Lin

Figure 2 for Linguistically Driven Graph Capsule Network for Visual Question Reasoning

Figure 3 for Linguistically Driven Graph Capsule Network for Visual Question Reasoning

Figure 4 for Linguistically Driven Graph Capsule Network for Visual Question Reasoning

* Submitted to TPAMI 2020. We have achieved an end-to-end interpretable structural reasoning for general images without the requirement of layout annotations

Access Paper or Ask Questions

Vision-Dialog Navigation by Exploring Cross-modal Memory

Mar 15, 2020
Yi Zhu, Fengda Zhu, Zhaohuan Zhan, Bingqian Lin, Jianbin Jiao, Xiaojun Chang, Xiaodan Liang

Figure 2 for Vision-Dialog Navigation by Exploring Cross-modal Memory

Figure 3 for Vision-Dialog Navigation by Exploring Cross-modal Memory

Figure 4 for Vision-Dialog Navigation by Exploring Cross-modal Memory

* CVPR2020

Access Paper or Ask Questions

Learning Reinforced Agents with Counterfactual Simulation for Medical Automatic Diagnosis

Mar 14, 2020
Junfan Lin, Ziliang Chen, Xiaodan Liang, Keze Wang, Liang Lin

Figure 2 for Learning Reinforced Agents with Counterfactual Simulation for Medical Automatic Diagnosis

Figure 3 for Learning Reinforced Agents with Counterfactual Simulation for Medical Automatic Diagnosis

Figure 4 for Learning Reinforced Agents with Counterfactual Simulation for Medical Automatic Diagnosis

* Submitted to TPAMI 2020. In the experiments, our trained agent achieves the new state-of-the-art under various experimental settings and possesses the advantage of sample-efficiency and robustness compared to other existing MAD methods

Access Paper or Ask Questions

Dynamic Knowledge Routing Network For Target-Guided Open-Domain Conversation

Mar 06, 2020
Jinghui Qin, Zheng Ye, Jianheng Tang, Xiaodan Liang

Figure 2 for Dynamic Knowledge Routing Network For Target-Guided Open-Domain Conversation

Figure 3 for Dynamic Knowledge Routing Network For Target-Guided Open-Domain Conversation

Figure 4 for Dynamic Knowledge Routing Network For Target-Guided Open-Domain Conversation

* 8 pages, 2 figues, 6tables, AAAI2020, fix our model's abbreviation

Access Paper or Ask Questions

ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection

Mar 03, 2020
Chenhan Jiang, Shaoju Wang, Hang Xu, Xiaodan Liang, Nong Xiao

Figure 2 for ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection

Figure 3 for ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection

Figure 4 for ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection

* 7 pages, 5 figure, AAAI2020

Access Paper or Ask Questions

Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN

Feb 18, 2020
Hang Xu, Linpu Fang, Xiaodan Liang, Wenxiong Kang, Zhenguo Li

Figure 2 for Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN

Figure 3 for Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN

Figure 4 for Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN

* Accepted by AAAI20

Access Paper or Ask Questions

SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection

Nov 30, 2019
Lewei Yao, Hang Xu, Wei Zhang, Xiaodan Liang, Zhenguo Li

Figure 2 for SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection

Figure 3 for SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection

Figure 4 for SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection

* Accepted by AAAI 2020

Access Paper or Ask Questions

Blockwisely Supervised Neural Architecture Search with Knowledge Distillation

Nov 29, 2019
Changlin Li, Jiefeng Peng, Liuchun Yuan, Guangrun Wang, Xiaodan Liang, Liang Lin, Xiaojun Chang

Figure 2 for Blockwisely Supervised Neural Architecture Search with Knowledge Distillation

Figure 3 for Blockwisely Supervised Neural Architecture Search with Knowledge Distillation

Figure 4 for Blockwisely Supervised Neural Architecture Search with Knowledge Distillation

* We achieve a state-of-the-art 78.4% top-1 accuracy on ImageNet in a mobile setting, which is about a 2.1% gain over EfficientNet-B0

Access Paper or Ask Questions

Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks

Nov 28, 2019
Fengda Zhu, Yi Zhu, Xiaojun Chang, Xiaodan Liang

Figure 2 for Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks

Figure 3 for Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks

Figure 4 for Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks

Access Paper or Ask Questions