Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Sheth, Ivaxi"'
Scientific discovery is a catalyst for human intellectual advances, driven by the cycle of hypothesis generation, experimental design, data evaluation, and iterative assumption refinement. This process, while crucial, is expensive and heavily depende
Externí odkaz:
http://arxiv.org/abs/2409.02604
With the recent emergence of powerful instruction-tuned large language models (LLMs), various helpful conversational Artificial Intelligence (AI) systems have been deployed across many applications. When prompted by users, these AI systems successful
Externí odkaz:
http://arxiv.org/abs/2402.18216
Autor:
Sheth, Ivaxi, Kahou, Samira Ebrahimi
The increasing use of neural networks in various applications has lead to increasing apprehensions, underscoring the necessity to understand their operations beyond mere final predictions. As a solution to enhance model transparency, Concept Bottlene
Externí odkaz:
http://arxiv.org/abs/2311.11108
Autor:
Sevyeri, Laya Rafiee, Sheth, Ivaxi, Farahnak, Farhood, Kahou, Samira Ebrahimi, Enger, Shirin Abbasinejad
Advancements in deep learning techniques have given a boost to the performance of anomaly detection. However, real-world and safety-critical applications demand a level of transparency and reasoning beyond accuracy. The task of anomaly detection (AD)
Externí odkaz:
http://arxiv.org/abs/2310.10702
Autor:
Antensteiner, Doris, Halawa, Marah, Aslam, Asra, Sheth, Ivaxi, Herath, Sachini, Huang, Ziqi, Kim, Sunnie S. Y., Akula, Aparna, Wang, Xin
In this paper, we present the details of Women in Computer Vision Workshop - WiCV 2023, organized alongside the hybrid CVPR 2023 in Vancouver, Canada. WiCV aims to amplify the voices of underrepresented women in the computer vision community, fosteri
Externí odkaz:
http://arxiv.org/abs/2309.12768
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
Autor:
Subramanian, Jithendaraa, Annadani, Yashas, Sheth, Ivaxi, Ke, Nan Rosemary, Deleu, Tristan, Bauer, Stefan, Nowrouzezahrai, Derek, Kahou, Samira Ebrahimi
Causal learning has long concerned itself with the accurate recovery of underlying causal mechanisms. Such causal modelling enables better explanations of out-of-distribution data. Prior works on causal learning assume that the high-level causal vari
Externí odkaz:
http://arxiv.org/abs/2210.13583
Autor:
Antensteiner, Doris, Bucci, Silvia, Goel, Arushi, Halawa, Marah, Kalavakonda, Niveditha, Kasarla, Tejaswi, Liu, Miaomiao, Samet, Nermin, Sheth, Ivaxi
In this paper, we present the details of Women in Computer Vision Workshop - WiCV 2022, organized alongside the hybrid CVPR 2022 in New Orleans, Louisiana. It provides a voice to a minority (female) group in the computer vision community and focuses
Externí odkaz:
http://arxiv.org/abs/2208.11388
Autor:
Subramanian, Jithendaraa, Annadani, Yashas, Sheth, Ivaxi, Bauer, Stefan, Nowrouzezahrai, Derek, Kahou, Samira Ebrahimi
Learning predictors that do not rely on spurious correlations involves building causal representations. However, learning such a representation is very challenging. We, therefore, formulate the problem of learning a causal representation from high di
Externí odkaz:
http://arxiv.org/abs/2207.05723