Efficient Deep Learning

Research Highlights (back to Research Overview)

Please find more publication and technical reports on Google Scholar. Some of our codes and datasets are available at GitHub.

Abbreviations: [C]: Conference; [J] Journal; [W] Workshop; [TR]: Technical Report; [B]: Book; [P]: Patent; [Comp]: Competition; [Proj]: Project; [Org] Program Organization; [SOTA]: State-of-the-art (at the time of publication)

MODEL Efficiency

(faster and smaller model with high accuracy, model compression, etc.)

• [J] CCNet: Criss-Cross Attention for Semantic Segmentation, Zilong Huang, Xinggang Wang, Yunchao Wei, Lichao Huang, Humphrey Shi, Wenyu Liu, Thomas S. Huang, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020 (SOTA on semantic segmentation, top journal in computer science, impact factor 19.42)

• [C] Motion Pyramid Networks for Accurate and Efficient Cardiac Motion Estimation, Hanchao Yu, Xiao Chen, Humphrey Shi, Terrence Chen, Thomas Huang, Shanhui Sun, MICCAI, 2020

• [TR] Any-Precision Deep Neural Networks, Haichao Yu, Haoxiang Li, Honghui Shi, Thomas S. Huang, Gang Hua, ArXiv Preprint, 2019

• [C] SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems, Xiaofan Zhang, Haoming Lu, Cong Hao, Jiachen Li, Bowen Cheng, Yuhong Li, Kyle Rupnow, Jinjun Xiong, Thomas Huang, Honghui Shi, Wen-mei Hwu, Deming Chen, MLSys, 2020 (Oral and Poster, acceptance rate 20.0 %)

• [C] SPGNet: Semantic Prediction Guidance for Scene Parsing, Bowen Cheng, Liang-Chieh Chen, Yunchao Wei, Yukun Zhu, Zilong Huang, Jinjun Xiong, Thomas Huang, Wen-mei Hwu, Honghui Shi, ICCV, 2019 (SOTA on Cityscapes, acceptance rate 25.0 %)

• [C] Balanced Two-Stage Residual Networks for Image Super-Resolution, Yuchen Fan, Honghui Shi, Jiahui Yu, Ding Liu, Wei Han, Haichao Yu, Zhangyang Wang, Xinchao Wang, Thomas S. Huang, CVPR Workshops, 2017

DATA Efficiency

(weakly supervised, semi-supervised, unsupervised and self-supervised learning, and domain adaptation etc.)

• [W] Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentation, Zhonghao Wang, Yunchao Wei, Rogerior Feris, Jinjun Xiong, Wen-Mei Hwu, Thomas S Huang, Honghui Shi, Visual Learning with Limited Labels @ CVPR, 2020 (SOTA on semi-supervised domain adaptation for semantic segmentation)

• [C] Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation, Zhonghao Wang, Mo Yu, Yunchao Wei, Rogerio Feris, Jinjun Xiong, Wen-mei Hwu, Thomas Huang, Honghui Shi, CVPR, 2020 (SOTA on unsupervised domain adaptation for semantic segmentation, acceptance rate 22.0 %)

• [C] Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-ID, Yang Fu, Yunchao Wei, Guanshuo Wang, Yuqian Zhou, Honghui Shi, Thomas Huang, ICCV, 2019 (SOTA on cross dataset re-id, Oral, acceptance rate 4.3 %)

• [C] Weakly Supervised Scene Parsing with Point-based Distance Metric Learning, Rui Qian, Yunchao Wei, Honghui Shi, Jiachen Li, Jiaying Liu, Thomas Huang, AAAI, 2019 (acceptance rate 16.2 %)

• [C] TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection, Yunchao Wei, Zhiqiang Shen, Bowen Cheng, Honghui Shi, Jinjun Xiong, Jiashi Feng, Thomas Huang, ECCV, 2018 (acceptance rate 31.8 %)

• [C] Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation, Yunchao Wei, Huaxin Xiao, Honghui Shi, Zequn Jie, Jiashi Feng, Thomas S. Huang, CVPR, 2018 (Spotlight Oral, acceptance rate 6.7 %)

LEARNING Efficiency

(learning from scratch, faster training, and transfer learning etc.)

• [C] FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimation, Hanchao Yu, Shanhui Sun, Haichao Yu, Xiao Chen, Honghui Shi, Thomas Huang, Terrence Chen, CVPR, 2020 (fast & online adaptation method, acceptance rate 22.0 %)

• [C] SpotTune: Transfer Learning through Adaptive Fine-tuning, Yunhui Guo, Honghui Shi, Abhishek Kumar, Kristen Grauman, Tajana Rosing, Rogerio Feris, CVPR, 2019 (SOTA on Visual Decathlon Challenge, acceptance rate 25.2 %)

• [C] Learning Object Detection from Scratch via Gated Feature Reuse , Zhiqiang Shen, Honghui Shi, Jiahui Yu, Hai Phan, Rogerio Feris, Liangliang Cao, Ding Liu, Xinchao Wang, Thomas S. Huang, Marios Savvides, BMVC, 2019

• [TR] Revisiting Pre-training: An Efficient Training Method for Image Classification, Bowen Cheng, Yunchao Wei, Honghui Shi, Shiyu Chang, Jinjun Xiong, Thomas S. Huang, ArXiv Preprint, 2018