Haozhe Liu

Haozhe Liu

Ph.D., AI Initiative KAUST

I am working towards a Ph.D. degree in AI Initiative, KAUST, under the supervision of Prof.Juergen Schmidhuber. I have published several papers in top-tier journals/conferences, including CVPR, ICCV, ECCV, AAAI, NeurIPS, MICCAI, TIP, TIFS, etc. I am a reviewer for CVPR, ECCV, ICCV, ICML, AAAI, and MICCAI. Previously, I interned at Jarvis Lab, Tencent, and was a visiting student at NBL, NTNU. My recent research interests include deep generative models and their security concerns. My long-term goal lies in making the learnable systems reliable, responsible, and explainable. My curriculum vitae can be found at here.

🔥 News

  • 2024.04:  🎉 Promote to Ph.D. Candidate!
  • 2024.02:  🎉 One paper is accepted by CVPR’2024!
  • 2024.02:  🎉🎉 I will join Meta as Research Scientist Intern on GenAI in Summer 2024!
  • 2023.12:  🎉 NLSOM is recognized as the best paper at NeurIPS’2023 workshop in Robustness of Few-shot/Zero-shot Learning in Foundation Models !
  • 2023.09:  🎉 One paper is accepted by NeurIPS’2023!
  • 2023.08:   Invited as a reviewer for AAAI’2024.
  • 2023.07:  🎉🎉 Two papers are accepted by ICCV’2023!.
  • 2023.05:  🎉 Our proposal w.r.t generative model is funded by SDAIA-KAUST Center of Excellence in Data Science and Artificial Intelligence (SDAIA-KAUST AI) (200k SAR, Co-PI with Bing Li).
  • 2023.02:  🎉🎉 Two papers are accepted by CVPR’2023!.
  • 2023.02:   Invited as a reviewer for ICCV’2023.
  • 2022.11:  🎉🎉 One paper is accepted by AAAI’2023 (Oral).
  • 2022.11:   Invited as a reviewer for CVPR’2023.
  • 2022.08:  🎉🎉 I join AI Initiative, KAUST to pursue the Ph.D. degree under the supervision of Juergen Schmidhuber!
  • 2022.08:  🎉 Our team reaches to the 4th/40 in NICO challenge (Invited Workshop Paper in ECCV’2022).
  • 2022.07:  🎉 One paper is accepted by ECCV’2022!
  • 2022.06:  🎉 Two papers are accepted by MICCAI’2022!
  • 2022.05:  Our method (Group-wise Inhibition) is merged into the official benchmark of ImageNet-C!
  • 2022.04:   Invited as a reviewer for ICML’2022, ECCV’2022 and MICCAI’2022.
  • 2021.10:   Invited as a reviewer for CVPR’2022.
  • 2021.07:  🎉 One paper is accepted by ICCV’2021!

đź“ť Publications

Journals: IEEE TIP x 1, IEEE TCYB x 1, IEEE TNNLS x 1, IEEE TIFS x 1, IEEE TIM x 1, MIA x 1, PR x 2.

Conferences: NeurIPS x 1, CVPR x 4, ICCV x 3, ECCV x 1, MICCAI x 2, AAAI x 1.

Selected Publications:

  • Liu, H., Zhuge, M., Li, B., Wang, Y., Faccio, F., Ghanem, B. & Schmidhuber, J. Learning to Identify Critical States for Reinforcement Learning from Videos ICCV’2023.

  • Liu, H., W Zhang, Li, B., Wu, H., He, N., Huang, Y., Li, Y., Ghanem, B. & Zheng, Y. AdaptiveMix: Improving GAN Training via Feature Space Shrinkage CVPR’2023.

  • Liu, H., Li, B., Wu, H., Liang, H., Huang, Y., Li, Y., … & Zheng, Y. Combating Mode Collapse in GANs via Manifold Entropy Estimation. AAAI’2023 Oral.

  • Liu, H., Wu, H., Xie, W., Liu, F., & Shen, L. Group-wise Inhibition based Feature Regularization for Robust Classification. ICCV’2021.

  • Liu, H., Zhang, W., Liu, F., Wu, H.,& Shen, L. (2021). Fingerprint Presentation Attack Detector Using Global-Local Model. IEEE T-CYB.

  • Liu, H., Zhang, W., Xie J., Wu, H., Li, B., Zhang, Z., Li, Y., Huang, Y., Ghanem, B., Y. Zheng. Decoupled Mixup for Out-of-Distribution Visual Recognition. ECCV’2022 Workshop.

  • Zhang, W., Liu, H.#, Xie, J., Faccio, F., Shou, M. Z., & Schmidhuber, J. (2024). Cross-Attention Makes Inference Cumbersome in Text-to-Image Diffusion Models. Technical Report. (# Corresponding Author)

  • Zhang, W.*, Liu, H.*, Li, B., Xie J., Huang, Y., Li, Y., Y. Zheng, Ghanem, B.. Dynamically Masked Discriminator for Generative Adversarial Networks NeurIPS’2023. (* Equal Contribution)

  • Zhuge, M.*, Liu, H.*, Faccio, F.*, Ashley, D. R.*, Csordás, R., Gopalakrishnan, A., … & Schmidhuber, J. (2023). Mindstorms in Natural Language-Based Societies of Mind. Position Paper, Best Paper@NeuralIPSW. (* Equal Contribution)

  • Wu, H.*, Chen, K.*, Liu, H.*, Zhuge, M.*, B Li, …, & Ghanem, B. NewsNet: A Novel Dataset for Hierarchical Temporal Segmentation CVPR’2023.(* Equal Contribution)

  • Ji, H.*, Liu, H.*, Li, Y.*, Xie J., He, N., Huang, Y., Dong, W., Chen, X., Shen L. & Zheng, Y. Point Beyond Class: A Benchmark for Weakly Semi-Supervised Abnormality Localization in Chest X-Rays. MICCAI’2022. (* Equal Contribution)

  • Zhang, W.*, Liu, H.*, Liu, F., Ramachandra, R., & Busch, C. Effective Presentation Attack Detection Driven by Face Related Task. ECCV’2022.(* Equal Contribution)

🎖 Honors and Awards

  • 2023 Best Paper Award at NeuralIPS Workshop in Robustness of Few-shot/Zero-shot Learning in Foundation Models
  • 2022 Outstanding Graduate Award (Rate<5%)
  • 2021 China National Scholarship (Rate<0.02%)
  • 2020 Excellent Academic Scholarship, First Class
  • 2019 Excellent Academic Scholarship, Second Class
  • 2018 National University Big Data Application Innovation Competition in Northwest, First Place

đź“– Research Experience

AI Initiative (KAUST)

PhD Candidate supervised by Prof. Juergen Schmidhuber.

  • Research Field includes explainable, reliable, and responsible AI.

  • Proposed Deep State Identifier to identify and recognize relevant states/actions/rewards for explaining the behavior given a policy. This project is accepted by ICCV’2023.

  • Contribute a large-scale Video Benchmark, NewsNet, for hierarchical video temporal segmentation, which is accepted by CVPR’2023. (I contribute most of my work before joining KAUST.)

Jarvis Lab (Tencent)

Internship supervised by Mentor: Dr. Yawen Huang, Dr. Nanjun He & Dr. Yuexiang Li and Director: Dr. Yefeng Zheng

  • Proposed AdaptiveMix to improve GAN training, which is accepted by CVPR’2023. (This project is cooperated with AI Initiative, KAUST.)

  • Proposed offline entropy estimation to combat mode collapse, which is accepted AAAI’2023. (This project is cooperated with AI Initiative, KAUST.)

  • Proposed Point Beyond Class to reduce the annotation cost for medical object detection, which is accepted by MICCAI’2022.

  • Participate to NICO Challenge (ECCV’2022 workshop), our team reach to 5th/40 in both tracks at Phase I, and 4th in Track 2 at Final Phase.

Norwegian Biometrics Laboratory (NTNU)

Visiting student supervised by Prof. Raghavendra Ramachandra and Prof. Christoph Busch

  • Proposed a self-supervised learning based method for face and fingerprint presentation attack detection, which is accepted by IEEE TNNLS.
  • Proposed a face presentation attack detector based on the taskonomy features, which is accepted by ECCV’2022.

Computer Vision Insitute (SZU)

M.S. supervised by Prof. Feng Liu and Prof. Linlin Shen

  • Proposed a regularization method to imporve the robustness of CNN based models, which is accepted by ICCV’2021 and open source.
  • Proposed a Manifold-preserved GANs to mitigate the mode collapse and gradient exploding.
  • Collected a famous presentation attack dataset based on OCT and for the first time established a one-class framework for OCT based PAD. This work is accepted by IEEE TIP
  • Proposed a presentation attack detector using Global-Local model, which reaches over 90% in terms of TDR@FDR=1% on LivDet2017 for the first time. (Accepted by IEEE TCYB)

đź’» Professional Service

Conference Reviewer

  • CVPR: 2022, 2023
  • ECCV: 2022, 2024
  • ICCV: 2023
  • AAAI: 2024
  • ICML: 2022
  • MICCAI: 2022