Research

Dynamic neural networks

Deep Networks with Stochastic Depth

Deep Networks with Stochastic Depth. Gao Huang*, Yu Sun*, Zhuang Liu, Daniel Sedra, Kilian Weinberger. European Conference on Computer Vision (ECCV Spotlight) 2016. (This paper was recommended as an Oral at NIPS 2016 Deep Learning Symposium)

CVBackbone Network for Vision

Snapshot Ensembles: Train 1, Get M for Free

Snapshot Ensembles: Train 1, Get M for Free. Gao Huang*, Yixuan Li*, Geoff Pleiss, Zhuang Liu, John E. Hopcroft, Kilian Weinberger. International Conference on Learning Representations (ICLR) 2017.

Densely Connected Convolutional Networks

Densely Connected Convolutional Networks. Gao Huang*, Zhuang Liu*, Laurens van der Maaten, Kilian Weinberger. IEEE Conference on Computer Vision and Pattern Recognition (CVPR Oral) 2017.

CVBackbone Network for Vision

Convolutional Networks with Dense Connectivity

Convolutional Networks with Dense Connectivity. Gao Huang, Zhuang Liu, Geoff Pleiss, Laurens Van Der Maaten, Kilian Q. Weingerger. IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI) 2019. (Journal version of DenseNet; Deep understanding of dense connectivity.)

CVBackbone Network for VisionDynamic neural networks

Improved Techniques for Training Adaptive Deep Networks

Improved Techniques for Training Adaptive Deep Networks. Hao Li*, Hong Zhang*, Xiaojuan Qi, Ruigang Yang, Gao Huang. International Conference on Computer Vision (ICCV) 2019.

CVDynamic neural networks

Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation

Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation. Zhenda Xie, Zheng Zhang, Xizhou Zhu, Gao Huang , Stephen Lin. European Conference on Computer Vision (ECCV Oral) 2020.

CVDynamic neural networks

Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification

Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification. Yulin Wang, Kangchen Lv, Rui Huang, Shiji Song, Le Yang, Gao Huang. Neural Information Processing Systems (NeurIPS) 2020.

CVDynamic neural networks

Resolution Adaptive Networks for Efficient Inference

Resolution Adaptive Networks for Efficient Inference. Le Yang*, Yizeng Han*, Xi Chen*, Shiji Song, Jifeng Dai, Gao Huang. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020.

Dynamic neural networksCV

Not All Images are Worth 16x16 Words: Dynamic Vision Transformers with Adaptive Sequence Length

Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition. Yulin Wang*, Rui Huang*, Shiji Song, Zeyi Huang, Gao Huang. Neural Information Processing Systems (NeurIPS) 2021.

Dynamic neural networksVision Transformer

Adaptive Focus for Efficient Video Recognition

Adaptive Focus for Efficient Video Recognition. Yulin Wang*, Zhaoxi Chen*, Haojun Jiang, Shiji Song, Yizeng Han, Gao Huang. International Conference on Computer Vision (ICCV Oral) 2021.

Dynamic neural networksCV

Regularizing Deep Networks with Semantic Data Augmentation

Regularizing Deep Networks with Semantic Data Augmentation. Yulin Wang*, Gao Huang*, Shiji Song, Xuran Pan, Yitong Xia, Cheng Wu. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021.

CVDynamic neural networks

Revisiting Locally Supervised Learning: an Alternative to End-to-end Training

Revisiting Locally Supervised Learning: an Alternative to End-to-end Training. Yulin Wang, Zanlin Ni, Shiji Song, Le Yang, Gao Huang. International Conference on Learning Representations (ICLR) 2021.

CVDynamic neural networks

Dynamic Neural Networks: A Survey

Dynamic Neural Networks: A Survey. Yizeng Han*, Gao Huang*, Shiji Song, Le Yang, Honghui Wang, Yulin Wang. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021

Dynamic neural networksCV

Spatially Adaptive Feature Refinement for Efficient Inference

Spatially Adaptive Feature Refinement for Efficient Inference. Yizeng Han, Gao Huang, Shiji Song, Le Yang, Yitian Zhang, Haojun Jiang. IEEE Transactions on Image Processing (TIP), 2021

Dynamic neural networksCV

RL

Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning

Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning. Wenjie Shi*, Shiji Song, Hui Wu, Ya-Chu Hsu, Cheng Wu, Gao Huang. 33rd Conference on Neural Information Processing Systems (NeurIPS), 2019.

Deep RL

Self-Attention-Based Temporary Curiosity in Reinforcement Learning Exploration

Self-Attention-Based Temporary Curiosity in Reinforcement Learning Exploration. Hangkai Hu*, Shiji Song, Gao Huang. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019.

Deep RL

Self-Supervised Discovering of Interpretable Features for Reinforcement Learning

Self-Supervised Discovering of Interpretable Features for Reinforcement Learning. Wenjie Shi*, Gao Huang, Shiji Song, Zhuoyuan Wang, Tingyu Lin, Cheng Wu. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2020.

InterpretabilityDeep RL

Meta-Reinforcement Learning With Dynamic Adaptiveness Distillation

Meta-Reinforcement Learning With Dynamic Adaptiveness Distillation. Hangkai Hu*, Gao Huang, Xiang Li, Shiji Song. IEEE Transactions on Neural Networks and Learning Sysytems (TNNLS) 2021.

Deep RL

Attention-Based Meta-Reinforcement Learning for Tracking Control of AUV With Time-Varying Dynamics

Attention-Based Meta-Reinforcement Learning for Tracking Control of AUV With Time-Varying Dynamics. Peng Jiang, Shiji Song, Gao Huang. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS(TNNLS) 2021.

Deep RL

Exploration With Task Information for Meta Reinforcement Learning

Exploration With Task Information for Meta Reinforcement Learning. Peng Jiang, Shiji Song, Gao Huang. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS(TNNLS) 2021.

Deep RL

Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning

Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning. Wenjie Shi*, Gao Huang*, Shiji Song, Cheng Wu. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2021.

InterpretabilityDeep RL

3D Computer Vision

Anytime Stereo Image Depth Estimation on Mobile Devices

Anytime Stereo Image Depth Estimation on Mobile Devices. Yan Wang, Zihang Lai, Gao Huang, Brian Wang, Laurens van der Maaten, Mark Campbell, Kilian Q. Weinberger. International Conference on Robotics and Automation (ICRA) 2019.

3D Object Detection with Pointformer

3D Object Detection with Pointformer. Xuran Pan*, Zhuofan Xia*, Shiji Song, Li Erran Li, Gao Huang. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021.

3D VisionCV

Backbone Network for Vision

Deep Networks with Stochastic Depth

CVBackbone Network for Vision

Densely Connected Convolutional Networks

Densely Connected Convolutional Networks. Gao Huang*, Zhuang Liu*, Laurens van der Maaten, Kilian Weinberger. IEEE Conference on Computer Vision and Pattern Recognition (CVPR Oral) 2017.

CVBackbone Network for Vision

Convolutional Networks with Dense Connectivity

CVBackbone Network for VisionDynamic neural networks

CondenseNet: An Efficient DenseNet using Learned Group Convolutions

CondenseNet: An Efficient DenseNet using Learned Group Convolutions. Gao Huang*, Shichen Liu*, Laurens van der Maaten, Kilian Q. Weinberger. IEEE Conference on Computer Vision and Pattern Recognition (CVPR Spotlight) 2018.

CVBackbone Network for VisionNetwork Pruning

Multi-Scale Dense Convolutional Networks for Resource Efficient Image Classification

Multi-Scale Dense Convolutional Networks for Resource Efficient Image Classification. Gao Huang, Danlu Chen, Tianhong Li, Felix Wu, Laurens van der Maaten, Kilian Q. Weinberger. International Conference on Learning Representations (ICLR Oral) 2018.

CVBackbone Network for Vision

Evolving Attention with Residual Convolutions

Evolving Attention with Residual Convolutions. Yujing Wang*, Yaming Yang*, Jiangang Bai, Mingliang Zhang, Jing Bai, Jing Yu, Ce Zhang, Gao Huang, Yunhai Tong. International Conference on Machine Learning (ICML) 2021.

CVBackbone Network for Vision

3D Object Detection with Pointformer

3D Object Detection with Pointformer. Xuran Pan*, Zhuofan Xia*, Shiji Song, Li Erran Li, Gao Huang. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021.

3D VisionCVBackbone Network for Vision

On the Integration of Self-Attention and Convolution

On the Integration of Self-Attention and Convolution. Xuran Pan, Chunjiang Ge, Rui Lu, Shiji Song, Guanfu Chen, Zeyi Huang, Gao Huang. Arxiv Preprint 2021.

Architecture DesignVision TransformerBackbone Network for Vision