My lab carries out fascinating research at the intersection of neuroscience and artificial intelligence.  We develop Neuro-Inspired AI models that can learn efficiently from multiple tasks.

Research topics include:


Selected publications 

Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method

K.Jeeveswaran, E.Arani*, B.Zonooz*

International Conference on Machine Learning (ICML, 2024)

[paper] [code] [short video]


The Effectiveness of Random Forgetting for Robust Generalization

V.Ramkumar, B.Zonooz*, E.Arani*

International Conference on Learning Representations (ICLR, 2024)

[paper] [code] [short video]


Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training

S.Gowda, B.Zonooz*, E.Arani*

International Conference on Learning Representations (ICLR, 2024)

[paper] [code] [short video]


TriRE: A Multi-Mechanism Learning Paradigm for Continual Knowledge Retention and Promotion

P.Vijayan, P.Bhat, B.Zonooz*, E.Arani*

Conference on Neural Information Processing Systems (NeurIPS, 2023)

[paper] [code] [short video]


BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning

K.Jeeveswaran, P.Bhat, B.Zonooz*, E.Arani*

International Conference on Machine Learning (ICML, 2023)

[paper] [code] [short video]

MTSL: Multi-Task Structural Learning using Local Task Similarity induced Neuron Creation and Removal

N.Gurulingan, B.Zonooz*, E.Arani*

International Conference on Machine Learning (ICML, 2023)

[paper] [code] [short video]

Learn, Unlearn and Relearn: An Online Learning Paradigm for Deep Neural Networks

V.Ramkumar, E.Arani*, B.Zonooz*

Transactions of Machine Learning Research (TMLR, 2023)

[paper] [code] [short video]

Task-Aware Information Routing from Common Representation Space in Lifelong Learning

Prashant Bhat, Bahram Zonooz*, Elahe Arani*

International Conference on Learning Representations (ICLR, 2023)

[paper] [code] [short video]

Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning

Fahad Sarfraz*, Elahe Arani*, Bahram Zonooz

International Conference on Learning Representations (ICLR, 2023)

[paper] [code] [short video]

Image Masking for Robust Self-Supervised Monocular Depth Estimation

Hemang Chawla, Kishaan Jeeveswaran, Elahe Arani*, Bahram Zonooz*

IEEE International Conference on Robotics and Automation (ICRA, 2023)

[paper] [code] [short video]

Sparse Coding in a Dual Memory System for Lifelong Learning

Fahad Sarfraz*, Elahe Arani*, Bahram Zonooz

(Oral) AAAI Conference on Artificial Intelligence (AAAI, 2023) 

[paper] [code] [short video]

A Comprehensive Study of Real-Time Object Detection Networks Across Multiple Domains: A Survey

Elahe Arani*, Shruthi Gowda*, Ratnajit Mukherjee, Omar Magdy, Senthilkumar Sockalingam Kathiresan, Bahram Zonooz

(Survey Certifications) Transactions on Machine Learning Research (TMLR) 

[paper] [short video]


Adversarial Attacks on Monocular Pose Estimation

Hemang Chawla, Arnav Verma, Elahe Arani*, Bahram Zonooz*

(Oral) IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022)

[paper] [code] [short video]


InBiaseD: Inductive Bias Distillation to Improve Generalization and Robustness through Shape-awareness

Shruthi Gowda, Bahram Zonooz*, Elahe Arani*

Conference on Lifelong Learning Agents (CoLLAs, 2022)

[paper] [code] [short video]


Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System

Elahe Arani*, Fahad Sarfraz*, Bahram Zonooz

Tenth International Conference on Learning Representations (ICLR, 2022)

[paper] [code] [short video]


UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial Attacks

Naresh Kumar Gurulingan*, Elahe Arani*, Bahram Zonooz

DeepMTL workshop (ICCV, 2021)

[paper] [short video]


Improving the efficiency of transformers for resource-constrained devices

Hamid Tabani, Ajay Balasubramaniam, Shabbir Marzban, Elahe Arani, Bahram Zonooz

(Oral) Euromicro DSD/SEAA 2021

[paper]


Distill on the Go: Online knowledge distillation in self-supervised

Prashant Bhat, Elahe Arani, Bahram Zonooz

(Spotlight) Learning from Limited or Imperfect Data (L2ID) Workshop (CVPR, 2021)

[paper] [code] [short video]


Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth and Ego-Motion Estimation

Hemang Chawla*, Arnav Verma*, Elahe Arani, Bahram Zonooz

(Oral) IEEE International Conference on Robotics and Automation (ICRA, 2021)

[paper] [code] [short video]


Adversarial Concurrent Training: Optimizing Robustness and Accuracy Trade-off of Deep Neural Networks

Elahe Arani*, Fahad Sarfraz*, Bahram Zonooz

British Machine Vision Conference (BMVC, 2020)

[paper] [code] [short video]


Crowdsourced 3D Mapping: A Combined Multi-View Geometry and Self-Supervised Learning Approach

Hemang Chawla, Matti Jukola, Terry Brouns, Elahe Arani, Bahram Zonooz

(Oral) International Conference on Intelligent Robots and Systems (IROS, 2020)

[paper] [short video]


Spectral weighting underlies perceived sound elevation

Bahram Zonooz, Elahe Arani, Knrad Kording, Remco Aalbers, Tansu Celikel, John Van Opstal

Nature Scientific Reports (2019)

[paper] 


Learning to localise weakly-informative sound spectra with and without feedback

Bahram Zonooz, Elahe Arani, John Van Opstal

Nature Scientific Reports (2018)

[paper]


Patents

 40+ patent applications