Searched for: author%3A%22Jamali-Rad%2C+H.%22
(1 - 8 of 8)
document
Shirekar, Ojas Kishorkumar (author), Singh, Anuj (author), Jamali-Rad, H. (author)
Humans have a unique ability to learn new representations from just a handful of examples with little to no supervision. Deep learning models, however, require an abundance of data and supervision to perform at a satisfactory level. Unsupervised few-shot learning (U-FSL) is the pursuit of bridging this gap between machines and humans. Inspired...
conference paper 2023
document
Falkena, Sieger (author), Jamali-Rad, H. (author), van Gemert, J.C. (author)
Binary Neural Networks (BNNs) are receiving an up-surge of attention for bringing power-hungry deep learning towards edge devices. The traditional wisdom in this space is to employ sign(.) for binarizing feature maps. We argue and illustrate that sign(.) is a uniqueness bottleneck, limiting information propagation throughout the network. To...
conference paper 2023
document
Jamali-Rad, H. (author), Abdizadeh, Mohammad (author), Sing, Anuj (author)
Classical federated learning approaches incur significant performance degradation in the presence of non-independent and identically distributed (non-IID) client data. A possible direction to address this issue is forming clusters of clients with roughly IID data. Most solutions following this direction are iterative and relatively slow, also...
journal article 2022
document
Shirekar, O.K. (author), Jamali-Rad, H. (author)
Unsupervised learning is argued to be the dark matter of human intelligence. To build in this direction, this paper focuses on unsupervised learning from an abundance of unlabeled data followed by few-shot fine-tuning on a downstream classification task. To this aim, we extend a recent study on adopting contrastive learning for self...
conference paper 2022
document
Szabó, A.D. (author), Jamali-Rad, H. (author), Mannava, Siva Datta (author)
Traditional empirical risk minimization (ERM) for semantic segmentation can disproportionately advantage or disadvantage certain target classes in favor of an (unfair but) improved overall performance. Inspired by the recently introduced tilted ERM (TERM), we propose tilted cross-entropy (TCE) loss and adapt it to the semantic segmentation...
conference paper 2021
document
Jamali-Rad, H. (author), Szabó, Attila (author)
Semantic segmentation is one of the most fundamental problems in computer vision with significant impact on a wide variety of applications. Adversarial learning is shown to be an effective approach for improving semantic segmentation quality by enforcing higher-level pixel correlations and structural information. However, state-of-the-art...
journal article 2021
document
Simonetto, A. (author), Jamali-Rad, H. (author)
Dual decomposition has been successfully employed in a variety of distributed convex optimization problems solved by a network of computing and communicating nodes. Often, when the cost function is separable but the constraints are coupled, the dual decomposition scheme involves local parallel subgradient calculations and a global subgradient...
journal article 2015
document
Jamali-Rad, H. (author)
Wireless networks have revolutionized nowadays world by providing real time cost-efficient service and connectivity. Even such an unprecedented level of service could not fulfill the insatiable desire of the modern world for more advanced technologies. As a result, a great deal of attention has been directed towards (mobile) wireless sensor...
doctoral thesis 2014
Searched for: author%3A%22Jamali-Rad%2C+H.%22
(1 - 8 of 8)