Da Li (李达)

Senior Research Scientist @ Samsung AI Centre, Cambridge

E-mail: dali.academic(at)gmail.com
Google Scholar

About Me

Da Li is a Senior Research Scientist within the Machine Learning and Data Intelligence group in Samsung AI Centre Cambridge, and also Visiting Scholars at Machine Intelligence Research group of the University of Edinburgh and at CVSSP of University of Surrey.

Da's research interests span transfer learning, meta learning and semi-supervised learning.

News

  • **Note** Previous 'PACS' google drive link has expired due to google's security update. The download link is updated now.
  • [01/2024] Our intern's work about "a hierarchical NAS for few shot learning" got accepted in ICLR 2024 as Oral!
  • [09/2023] Our intern's work "Better Practice DA" got Best Paper Award in AutoML 2023!
  • [06/2023] Appointed as a Visiting Lecturer at CVSSP of Surrey!
  • [06/2023] One paper about generalized FSL for segmentation is in TIP.
  • [05/2023] Better practice for domain adaptation is accepted in AutoML 2023.
  • [03/2023] Two papers accepted in CVPR 2023, including one highlight.
  • [01/2023] Two papers accepted in ICLR 2023, including one spotlight.
  • [12/2022] We are organizing the workshop "What do we need for successful domain generalization?"in ICLR23. Please see CFP.
  • [10/2022] Two Oral papers to appear in BMVC 2022.
  • [06/2022] One paper accepted in TIP.
  • [05/2022] One paper accepted in ICML 2022.
  • [03/2022] We have one internship available in SAIC-Cambridge for Self-supervised Learning or Federated Learning. Please contact me if interested!!!
  • [03/2022] One paper accepted in CVPR 2022.
  • [11/2021] One paper accepted in NeurIPS 2021 Datasets and Benchmarks track.
  • [10/2021] Serving as a Senior Program Committee (SPC) member for AAAI-22.
  • [08/2021] One paper proposing a simple feature augmentation for domain generalization is accepted in ICCV 2021.
  • [05/2021] One paper about adversarial robustness is accepted in ICML 2021. Congrats Panagiotis!
  • [12/2020] One paper about stochastic neural networks is accepted in AAAI 2021.
  • [10/2020] One paper about sketch based photo segmenter generation is accepted in TIP.
  • [07/2020] Our 'online Meta-DA for MSDA/SSDA' accepted in ECCV 2020.
  • [12/2019] Code released for our ICCV'19 paper "Episodic DG".
  • [11/2019] Code released for our ICCV'19 paper "Robust Person Re-identification".
  • [07/2019] Two papers accepted in ICCV 2019, including one oral.
  • [07/2019] Joined Machine Learning Group of SAIC-C as a Researcher working with Dr. Timothy Hospedales.
  • [01/2019] Joined SAIC-Cambridge as a Research Intern working with Prof. Tao Xiang.
  • [07/2018] Our paper accepted in ECCV 2018.
  • [06/2018] Code released for our AAAI 2018 paper "Meta DG".
  • [03/2018] Our paper has been selected for the spotlight presentation in CVPR 2018.
  • [03/2018] Awarded for the Rabin Ezra Scholarship.
  • [02/2018] One recent paper will appear in CVPR 2018.
  • [11/2017] One paper will appear in AAAI 2018.

Experience

  • Senior Research Scientist, Samsung AI Center, Cambridge, UK. 2022/March-Present.
  • Visiting Lecturer, CVSSP, Surrey, UK. 2023/June-Present.
  • Visiting Researcher, University of Edinburgh, UK. 2020/July-Present.
  • Research Scientist, Samsung AI Center, Cambridge, UK. 2019/July-2022/March.
  • Assistant Research Scientist, Samsung AI Center, Cambridge, UK. 2019/Jan-July.

Publication

*: Equal contribution. †: Corresponding author.

2023

Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn
Ondrej Bohdal*, Yinbing Tian*, Yongshuo Zong, Ruchika Chavhan, Da Li, Henry Gouk, Li Guo, Timothy Hospedales
Accepted in CVPR 2023

Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style
Fengyin Lin*, Mingkang Li*, Da Li†, Timothy Hospedales, Yi-Zhe Song, Yonggang Qi
Accepted in CVPR 2023 (Highlight)

Domain Generalisation via Domain Adaptation: An Adversarial Fourier Amplitude Approach
Minyoung Kim, Da Li, Timothy Hospedales
Accepted in ICLR 2023

SketchKnitter: Vectorized Sketch Generation with Diffusion Models
Qiang Wang, Haoge Deng, Yonggang Qi, Da Li, Yi-Zhe Song
Accepted in ICLR 2023 (Spotlight)

2022

Learning to Augment via Implicit Differentiation for Domain Generalization
T Wang, D Li, K Zhou, T Xiang, YZ Song
Accepted in BMVC 2022 (Oral)

Robust Target Training for Multi-Source Domain Adaptation
Z Deng, D Li, YZ Song, T Xiang
Accepted in BMVC 2022 (Oral)

Dynamic instance domain adaptation
Z Deng, K Zhou, D Li, J He, YZ Song, T Xiang
Accepted in TIP

Fisher sam: Information geometry and sharpness aware minimisation
M Kim, D Li, SX Hu, T Hospedales
Accepted in ICML 2022

Pushing the limits of simple pipelines for few-shot learning: External data and fine-tuning make a difference
SX Hu, D Li, J Stühmer, M Kim, TM Hospedales
Accepted in CVPR 2022

2021

A channel coding benchmark for meta-learning
R Li, O Bohdal, R Mishra, H Kim, D Li, N Lane, T Hospedales
Accepted in NeurIPS 2021 Datasets and Benchmarks track

A Simple Feature Augmentation for Domain Generalization
Pan Li*, Da Li*, Wei Li, Shaogang Gong, Yanwei Fu and Timothy Hospedales
Accepted in ICCV 2021

Weight-Covariance Alignment for Adversarially Robust Neural Networks
Panagiotis Eustratiadis, Henry Gouk, Da Li, Timothy Hospedales
Accepted in ICML 2021

Simple and Effective Stochastic Neural Networks
Tianyuan Yu, Yongxin Yang, Da Li, Timothy Hospedales and Tao Xiang
Accepted in AAAI 2021

2020

Sketch-a-Segmenter: Sketch-based Photo Segmenter Generation
Conghui Hu, Da Li, Yongxin Yang, Timothy Hospedales and Yi-Zhe Song
Accepted in Transactions on Image Processing

Sequential Learning for Domain Generalization
Da Li, Yongxin Yang, Yi-Zhe Song and Timothy Hospedales
Accepted in TASK-CV Workshop at ECCV 2020

Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation
Da Li, Timothy Hospedales
Accepted in ECCV 2020

2019

Robust Person Re-identification by Modelling Feature Uncertainty
Tianyuan Yu, Da Li, Yongxin Yang, Timothy Hospedales, Tao Xiang
Accepted in ICCV 2019
Code

Episodic training for domain generalization
Da Li, Jianshu Zhang, Yongxin Yang, Cong Liu, Yi-Zhe Song, Timothy M Hospedales
Accepted as an oral in ICCV 2019
Code

2018

Deep factorised inverse-sketching
Kaiyue Pang, Da Li, Jifei Song, Yi-Zhe Song, Tao Xiang, Timothy M Hospedales
Accepted in ECCV 2018

Sketch-a-Classifier: Sketch-based Photo Classifier Generation
Conghui Hu, Da Li, Yi-Zhe Song, Tao Xiang, Tim Hospedales
Accepted as a spotlight in Conference on Computer Vision and Pattern Recognition (CVPR 2018)

Learning to Generalize: Meta-Learning for Domain Generalization
Da Li, Yongxin Yang, Yi-Zhe Song and Timothy M. Hospedales
Accepted in AAAI Conference on Artificial Intelligence (AAAI 2018)
Code

2017

Deeper, Broader and Artier Domain Generalization
Da Li, Yongxin Yang, Yi-Zhe Song and Timothy M. Hospedales
International Conference on Computer Vision (ICCV), 2017.
Project

Now You See Me: Deep Face Hallucination for Unviewed Sketches
Conghui Hu, Da Li, Yi-Zhe Song and Timothy M. Hospedales
British Machine Vision Conference (BMVC) -- oral, 2017.

Services

Reviwers: BMVC, CVPR, NeurIPS, ICML, TPAMI, Machine Learning.

Senior Program Committee (SPC): AAAI 2022.