publications

2026

1. SIGGRAPH

   

   HairPort: In-context 3D-Aware Hair Import and Transfer for Images

   Alireza Heidari, A. Alimohammadi, W. Michel Pinto Lira, and 2 more authors

   In ACM SIGGRAPH, 2026

   Bib

   @inproceedings{heidari2026hairport,
     title = {HairPort: In-context 3D-Aware Hair Import and Transfer for Images},
     author = {Heidari, Alireza and Alimohammadi, A. and Lira, W. Michel Pinto and Bar-Lev, A. and Mahdavi-Amiri, A.},
     booktitle = {ACM SIGGRAPH},
     year = {2026},
     publisher = {ACM SIGGRAPH}
   }

2024

1. ICLR

   

   Unlabeled Out-of-Domain Data Improves Generalization

   Amir Hossein Saberi, Amir Najafi, Alireza Heidari, and 3 more authors

   In The Twelfth International Conference on Learning Representations, 2024

   Abs Bib HTML PDF

   We propose a novel framework for incorporating unlabeled data into semi-supervised classification problems, where scenarios involving the minimization of either i) adversarially robust or ii) non-robust loss functions have been considered. Notably, we allow the unlabeled samples to deviate slightly (in total variation sense) from the in-domain distribution. The core idea behind our framework is to combine Distributionally Robust Optimization (DRO) with self-supervised training. As a result, we also leverage efficient polynomial-time algorithms for the training stage. From a theoretical standpoint, we apply our framework on the classification problem of a mixture of two Gaussians in ℝd, where in addition to the m independent and labeled samples from the true distribution, a set of n (usually with n≫m) out of domain and unlabeled samples are given as well. Using only the labeled data, it is known that the generalization error can be bounded by ∝(d/m)1/2. However, using our method on both isotropic and non-isotropic Gaussian mixture models, one can derive a new set of analytically explicit and non-asymptotic bounds which show substantial improvement on the generalization error compared to ERM. Our results underscore two significant insights: 1) out-of-domain samples, even when unlabeled, can be harnessed to narrow the generalization gap, provided that the true data distribution adheres to a form of the “cluster assumption", and 2) the semi-supervised learning paradigm can be regarded as a special case of our framework when there are no distributional shifts. We validate our claims through experiments conducted on a variety of synthetic and real-world datasets.

   @inproceedings{saberi2024outofdomain,
     title = {Unlabeled Out-of-Domain Data Improves Generalization},
     author = {Saberi, Amir Hossein and Najafi, Amir and Heidari, Alireza and Movasaghinia, Mohammad Hosein and Motahari, Abolfazl and Khalaj, Babak},
     booktitle = {The Twelfth International Conference on Learning Representations},
     year = {2024},
     url = {https://openreview.net/forum?id=Bo6GpQ3B9a},
     publisher = {International Conference on Learning Representations}
   }