Saad Hossain
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Saad Hossain has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Sirisha Rambhatla
University of Waterloo
3 shared publications - Kimathi Kaai
Department of Systems Design Engineering, University of Waterloo, Waterloo, ON, Canada
2 shared publications - Jinman Park
University of Waterloo, Waterloo, ON, Canada
1 shared publication - Kellin Pelrine
Mila - Québec AI Institute, Montréal, Québec, Canada
1 shared publication - Matthew Kowal
FAR.AI, Berkeley, USA
1 shared publication - Nayeema Nonta
Critical ML Lab, University of Waterloo, Waterloo, Canada
1 shared publication
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9036-9047
TamperBench : Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9036-9047
Open AccessTamperBench : Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
- Open Access
- 11 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (11) , 9894-9905
Bringing Equity to Classification: Domain Generalization for Domain-Linked Classes
Domain generalization (DG) focuses on transferring domain-invariant knowledge from multiple source (training) domains to an a priori unseen target domain(s). This task implicitly requires that classes of interest are expressed in multiple sources (domain-shared) to break spurious domain-class correlations. However, real-world data scarcity challenges may often result in classes present in only a specific domain (domain-linked), which we show leads to extremely poor generalization. In this work, we introduce the domain-linked DG task to the community and develop a methodology to learn useful domain-invariant representations from domain-shared classes for domain-linked ones. Specifically, we propose FOND, a Fairness-inspired and cONtrastive learning objective for Domain-linked DG. Rigorous and reproducible experimental results communicate that FOND accomplishes state-of-the-art improvements for domain-linked classes, given a sufficient number of domain-shared classes and with minimal performance trade-offs. Complementary to these contributions, we theoretically analyze this task and provide practical insights for domain-linked class generalizability.
- 11 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (11) , 9894-9905
Open AccessBringing Equity to Classification: Domain Generalization for Domain-Linked Classes
Domain generalization (DG) focuses on transferring domain-invariant knowledge from multiple source (training) domains to an a priori unseen target domain(s). This task implicitly requires that classes of interest are expressed in multiple sources (domain-shared) to break spurious domain-class correlations. However, real-world data scarcity challenges may often result in classes present in only a specific domain (domain-linked), which we show leads to extremely poor generalization. In this work, we introduce the domain-linked DG task to the community and develop a methodology to learn useful domain-invariant representations from domain-shared classes for domain-linked ones. Specifically, we propose FOND, a Fairness-inspired and cONtrastive learning objective for Domain-linked DG. Rigorous and reproducible experimental results communicate that FOND accomplishes state-of-the-art improvements for domain-linked classes, given a sufficient number of domain-shared classes and with minimal performance trade-offs. Complementary to these contributions, we theoretically analyze this task and provide practical insights for domain-linked class generalizability.
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1837-1849
Domain-Guided Spatio-Temporal Self-Attention for Egocentric 3D Pose Estimation
Vision-based ego-centric 3D human pose estimation (ego-HPE) is essential to support critical applications of xR-technologies. However, severe self-occlusions and strong distortion introduced by the fish-eye view from the head mounted camera, make ego-HPE extremely challenging. To address these challenges, we propose a domain-guided spatio-temporal transformer model that leverages information specific to ego-views. Powered by this domain-guided transformer, we build Egocentric Spatio-Temporal Self-Attention Network (Ego-STAN), which uses 2D image representations and spatio-temporal attention to address both distortions and self-occlusions in ego-HPE. Additionally, we introduce a spatial concept called feature map tokens (FMT) which endows Ego-STAN with the ability to draw complex spatio-temporal information encoded in ego-centric videos. Our quantitative evaluation on the contemporary xR-EgoPose dataset, achieves a 38.2% improvement on the highest error joints against the SOTA ego-HPE model, while accomplishing a 22% decrease in the number of parameters. Finally, we also demonstrate the generalization capabilities of our model to real-world HPE tasks beyond ego-views achieving 7.7% improvement on 2D human pose estimation with the Human3.6M dataset. Our code is also made available at: https://github.com/jmpark0808/Ego-STAN
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1837-1849
Open AccessDomain-Guided Spatio-Temporal Self-Attention for Egocentric 3D Pose Estimation
Vision-based ego-centric 3D human pose estimation (ego-HPE) is essential to support critical applications of xR-technologies. However, severe self-occlusions and strong distortion introduced by the fish-eye view from the head mounted camera, make ego-HPE extremely challenging. To address these challenges, we propose a domain-guided spatio-temporal transformer model that leverages information specific to ego-views. Powered by this domain-guided transformer, we build Egocentric Spatio-Temporal Self-Attention Network (Ego-STAN), which uses 2D image representations and spatio-temporal attention to address both distortions and self-occlusions in ego-HPE. Additionally, we introduce a spatial concept called feature map tokens (FMT) which endows Ego-STAN with the ability to draw complex spatio-temporal information encoded in ego-centric videos. Our quantitative evaluation on the contemporary xR-EgoPose dataset, achieves a 38.2% improvement on the highest error joints against the SOTA ego-HPE model, while accomplishing a 22% decrease in the number of parameters. Finally, we also demonstrate the generalization capabilities of our model to real-world HPE tasks beyond ego-views achieving 7.7% improvement on 2D human pose estimation with the Human3.6M dataset. Our code is also made available at: https://github.com/jmpark0808/Ego-STAN