Zobrazeno 1 - 10
of 85
pro vyhledávání: '"Havaei, Mohammad"'
Autor:
Humayun, Ahmed Imtiaz, Amara, Ibtihel, Schumann, Candice, Farnadi, Golnoosh, Rostamzadeh, Negar, Havaei, Mohammad
Deep generative models learn continuous representations of complex data manifolds using a finite number of samples during training. For a pre-trained generative model, the common way to evaluate the quality of the manifold representation learned, is
Externí odkaz:
http://arxiv.org/abs/2408.08307
The rise of foundation models holds immense promise for advancing AI, but this progress may amplify existing risks and inequalities, leaving marginalized communities behind. In this position paper, we discuss that disparities towards marginalized com
Externí odkaz:
http://arxiv.org/abs/2406.01757
Deep learning classifiers are prone to latching onto dominant confounders present in a dataset rather than on the causal markers associated with the target class, leading to poor generalization and biased predictions. Although explainability via coun
Externí odkaz:
http://arxiv.org/abs/2405.09288
Autor:
Sevyeri, Laya Rafiee, Sheth, Ivaxi, Farahnak, Farhood, See, Alexandre, Kahou, Samira Ebrahimi, Fevens, Thomas, Havaei, Mohammad
While neural networks are capable of achieving human-like performance in many tasks such as image classification, the impressive performance of each model is limited to its own dataset. Source-free domain adaptation (SFDA) was introduced to address k
Externí odkaz:
http://arxiv.org/abs/2304.02798
Humans have perfected the art of learning from multiple modalities through sensory organs. Despite their impressive predictive performance on a single modality, neural networks cannot reach human level accuracy with respect to multiple modalities. Th
Externí odkaz:
http://arxiv.org/abs/2211.15071
Federated learning aims to train predictive models for data that is distributed across clients, under the orchestration of a server. However, participating clients typically each hold data from a different distribution, which can yield to catastrophi
Externí odkaz:
http://arxiv.org/abs/2211.00184
Autor:
Shakeri, Fereshteh, Boudiaf, Malik, Mohammadi, Sina, Sheth, Ivaxi, Havaei, Mohammad, Ayed, Ismail Ben, Kahou, Samira Ebrahimi
Few-shot learning has recently attracted wide interest in image classification, but almost all the current public benchmarks are focused on natural images. The few-shot paradigm is highly relevant in medical-imaging applications due to the scarcity o
Externí odkaz:
http://arxiv.org/abs/2206.00092
Autor:
Varno, Farshid, Saghayi, Marzie, Sevyeri, Laya Rafiee, Gupta, Sharut, Matwin, Stan, Havaei, Mohammad
In Federated Learning (FL), a number of clients or devices collaborate to train a model without sharing their data. Models are optimized locally at each client and further communicated to a central hub for aggregation. While FL is an appealing decent
Externí odkaz:
http://arxiv.org/abs/2204.13170
Diversity in data is critical for the successful training of deep learning models. Leveraged by a recurrent generative adversarial network, we propose the CT-SGAN model that generates large-scale 3D synthetic CT-scan volumes ($\geq 224\times224\times
Externí odkaz:
http://arxiv.org/abs/2110.09288
We propose a hypothesis disparity regularized mutual information maximization~(HDMI) approach to tackle unsupervised hypothesis transfer -- as an effort towards unifying hypothesis transfer learning (HTL) and unsupervised domain adaptation (UDA) -- w
Externí odkaz:
http://arxiv.org/abs/2012.08072