Ehsan Abbasnejad
Ehsan Abbasnejad
Senior Lecturer (North American Assoc. Prof.)
Future Making Fellow
Director of Responsible Machine Learning
Australian Institute for Machine Learning (AIML), University of Adelaide
Principal Researcher & Team Lead,
Centre for Augmented Reasoning (CAR)  
email: ehsan (dot) abbasnejad (AT) adelaide (dot) edu (dot) au

I am interested in machine learning and its applications. I have had the experience of working at Australian National University (ANU), NICTA (currently Data61), Microsoft Research, Xerox Research and NEC Labs America prior to joining AIML.

We are actively looking for PhD and postdoc candidates. If you are interested, feel free to contact me.

News

  • I won an Australian Council's Discovery Project (DP) to explore imagination in Reinforcement Learning.
  • I won CSIRO's Next Generation Graduates Fund to support Honours and MSc research students.
  • I am serving as Area Chair for CVPR, NeurIPS and WACV starting 2023.
  • I am teaching Introduction to Statistical Machine Learning this semester.
  • Finalist in Bushfire Data Quest. (August, 2020) [video of our presentation]
  • We won merit prize at the OzMineral Explorer Challenge. (July, 2020)
  • Won 2nd Prize of OZ Minerals Explorer Challenge as a member of DeepSightX team. (June, 2019) [News details] [Media]

Selected Publications [Full list in Google Scholar]

  • D. Teney, J. Wang, E Abbasnejad, Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup,  International Conference on Machine Learning (ICML) 2024. [Link]
  • D. Teney, A. Nicolicioiu, V. Hartmann, E Abbasnejad, Neural Redshift: Random Networks are not Random Functions,  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) [Oral] 2024. [Link]
  • V. Vo, E. Abbasnejad, D. Ranasinghe, BRUSLEATTACK: Query-efficient Score-based Sparse Adversarial Attack,  The Twelfth International Conference on Learning Representations (ICLR) 2024. [Link]
  • D. Teney, Y. Lin, S. J. Oh, E. Abbasnejad, ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets,  Conference on Neural Information Processing Systems (NeurIPS) 2023. [Link]
  • M. McDonnell, D. Gong, A. Parveneh, E. Abbasnejad, A. van den Hengel, RanPAC: Random Projections and Pre-trained Models for Continual Learning,  Conference on Neural Information Processing Systems (NeurIPS) 2023. [Link]
  • S. Herath, B. Fernando, E. Abbasnejad, M. Hayat, S. Khadivi, M. Harandi, H. Rezatofighi, G. Haffari, Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation,  Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) 2023. [Link]
  • I. Nassar, M. Hayat, E. Abbasnejad, H. Rezatofighi, G. Haffari, ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning,  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) [Highlight], 2023. [Link]
  • B. G. Doan, S. Yang, P. Montague, O. De Vel, T. Abraham, E. Abbasnejad, D. Ranasinghe, Feature-Space Bayesian Adversarial Learning Improved Malware Detector Robustness,  Association for the Advancement of Artificial Intelligence (AAAI) 2023. [Link]
  • Z. Zhang, I. Ng, D. Gong, Y. Liu, E. Abbasnejad, M. Gong, K. Zhang, J. Shi, Truncated Matrix Power Iteration for Differentiable DAG Learning,  Conference on Neural Information Processing Systems (NeurIPS) 2022. [Link]
  • D. Teney, M. Peyrard, E. Abbasnejad, Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning,  European Conference on Computer Vision (ECCV) 2022. [Link]
  • B. G. Doan, E. Abbasnejad, D. Ranasinghe, Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense,  International Conference on Machine Learning (ICML) 2022. [Link]
  • D. Teney, E. Abbasnejad, S. Lucey, A. van den Hengel, Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization,  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022. [Link]
  • A. Parvaneh, E. Abbasnejad, D. Teney, R. Haffari, A. van den Hengel, J. Shi, Active Learning by Feature Mixing,  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022. [Link]
  • V. Q. Vo, E. Abbasnejad, D. Ranasinghe, Query Efficient Decision Based Sparse Attacks Against Black-Box Deep Learning Models,  International Conference on Representation Learning (ICLR) 2022. [Link]
  • V. Q. Vo, E. Abbasnejad, D. Ranasinghe, RamBoAttack: A Robust and Query Efficient Deep Neural Network Decision Exploit,  The Network and Distributed System Security Symposium (NDSS) 2022. Link]
  • D. Teney, E. Abbasnejad, A. van den Hengel, Unshuffling data for improved generalization in visual question answering, International Conference on Computer Vision (ICCV), 2021 [Link]
  • M. Zhang, S. Su, S. Pan, X. Chang, E. Abbasnejad, G. Haffari, iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients,  International Conference on Machine Learning (ICML), 2021.
  • I. Nassar, S. Herath, E. Abbasnejad, W. Buntine, G. Haffari, All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training,  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), [Oral], 2021. [Link]
  • A. Parvaneh, E. Abbasnejad, Q. Wu, Q. Shi, A. van den Hengel, Show, Price and Negotiate: A Negotiator with Online Value Look-Ahead,  IEEE Transactions on Multimedia, 2021. [Link]
  • M. Neshata, M. Nezhad, E. Abbasnejad, S. Mirjalilide, D. Groppi, A. Heydari, L. Tjernberg,D. Garcia, B. Alexandera, Q. Shi, M. Wagner, Wind turbine power output prediction using a new hybrid neuro-evolutionary method,  Energy, Volume 229, 2021. [Link]
  • M. Neshata, M. Nezhad, E. Abbasnejad, S. Mirjalilide, L. Tjernberg,D. Garcia, B. Alexandera, M. Wagner, A deep learning-based evolutionary model for short-term wind speed forecasting: A case study of the Lillgrund offshore wind farm,  Energy Conversion and Management, 2021. [Link]
  • A. Parvaneh, E. Abbasnejad, D. Teney, Q. Shi, A. van den Hengel, Counterfactual Vision-and-Language Navigation: Unraveling the Unseen,  Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), 2020. [Spotlight] [Link]
  • D. Teney, K. Kafle, R. Shrestha, E. Abbasnejad, C. Kanan, A. van den Hengel, On the Value of Out-of-Distribution Testing: An Example of Goodhart’s Law, Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), 2020. [Link]
  • D. Teney, E. Abbasnejad, A. van den Hengel, Learning what makes a difference from counterfactual examples and gradient supervision, European Conference on Computer Vision (ECCV), 2020 [Link]
  • E. Abbasnejad, D. Teney, A. Parvaneh, Q. Shi, A. van den Hengel, Counterfactual Vision and Language Learning, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. [Oral][Link]
  • E. Abbasnejad, I. Abbasnejad, Q. Wu, Q. Shi, A. van den Hengel, Gold Seeker: Information Gain from Policy Distributions for Goal-oriented Vision-and-Language Reasoning, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. [Link]
  • B. Doan, E. Abbasnejad, D. Ranasinghe, Februus: Input Purification Defense Against Trojan Attacks on Deep Neural Network, 36th Annual Computer Security Applications Conference (ACSAC), 2020. [Link]
  • M. Kazemi, Q. Wu, E. Abbasnejad, Q. Shi, Optimistic Agent: Accurate Graph-Based Value Estimation for More Successful Visual Navigation, Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021. [Link]
  • E. Abbasnejad, Q. Shi, A. van den Hengel, L. Liu, GADE: A Generative Adversarial Approach to Density Estimation and its Applications, International Journal of Computer Vision 128 (10), 2731-2743, 2020. [Link]
  • E. Abbasnejad, Q. Shi, A. van den Hengel, L. Liu, A Generative Adversarial Density Estimator, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019. [Oral] [Link]
  • E. Abbasnejad, Q. Wu, Q. Shi, A. van den Hengel, L. Liu, What's to Know? Uncertainty as a Guide to Asking Goal-Oriented Questions, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019. [Link]
  • E. Abbasnejad, A. Dick, Q. Shi, A. van den Hengel, Active Learning from Noisy Tagged Images, In Proceedings of British Machine Vision Conference (BMVC), Newcastle, UK, 2018. [Link]
  • M. Abdi, E. Abbasnejad, C. P. Lim, S. Nahavandi, 3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space, In Proceedings of British Machine Vision Conference (BMVC). Newcastle, UK, 2018. [Oral] [Link]
  • A. Abedin, E. Abbasnejad, Q. Shi, D. Ranasinghe, H. Rezatofighi, Deep Auto-Set: A Deep Auto-Encoder-Set Network for Activity Recognition Using Wearables , In Proceedings of the 15th EAI International Conference on Mobile and Ubiquitous Systems (MobiQuitous), New York, NY, USA, 2018. [Link]
  • E. Abbasnejad, A. Dick, A. van den Hengel, Infinite Variational Autoencoder for Semi-Supervised Learning , The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, USA, 2017. [link] [supplement
  • A. Niculescu-Mizil, E. Abbasnejad, Label Filters for Large Scale Multilabel Classification , In Proceedings of The 20th International Conference on Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, USA, 2017. [Link
  • H. Rezatofighi, V. Kumar, A. Milan, E. Abbasnejad, A. Dick, I. Reid, DeepSetNet: Predicting Sets with Deep Neural Networks, The IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017. [link]
  • A. Khoshkbarforoushha, R. Ranjan, R. Gaire, E. Abbasnejad, L. Wang, A. Zomaya, Distribution Based Workload Modelling of Continuous Queries in Clouds , In IEEE Transactions on Emerging Topics in Computing, 2016. [link]
  • E. Abbasnejad, J. Domke, S. Sanner, Loss-calibrated Monte Carlo Action Selection , In Proceedings of the 26th Conference on Artificial Intelligence (AAAI), Austin, USA, 2015. [link]
  • H. Afshar, S. Sanner, E. Abbasnejad, Linear-time Gibbs Sampling in Piecewise Graphical Models , In Proceedings of the 26th Conference on Artificial Intelligence (AAAI), Austin, USA, 2015. [link]
  • E. Abbasnejad, E. V. Bonilla, S. Sanner, Decision-theoretic Sparsification for Gaussian Process Preference Learning , Proceedings of the Machine Learning and Knowledge Discovery in Databases - European Conference (ECML PKDD). Prague, Czech Republic, 2013. [link]
  • E. Abbasnejad, S. Sanner, E. V. Bonilla, P. Poupart, Learning Community-based Preferences via Dirichlet Process Mixtures of Gaussian Processes , In Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI), Beijing, China, 2013. [link] [dataset]

Research Group

Alumni

  • Mohamed Khalil Jabri, PhD Student (2020-2023) Joint with IMT-Atlantique, France
  • Viet Quoc Vo, PhD Student (2019-2023)
  • Amin Parvaneh, PhD (2018-2022).
  • Narjess Askari, PhD (2020-2022).
  • Bao G. Doan, PhD (2018-2022)
  • Jinan Zou, PhD (2019-2023)
  • Adrian Orenstein, Msc (2020-2023)
  • Shahdad Ghassemzadeh, PhD (2017-2020)