Zobrazeno 1 - 10
of 6 486
pro vyhledávání: '"Etemad, A"'
In this paper, we propose a novel approach, Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training (FedSB), to address the challenges of data heterogeneity within a federated learning framework. FedSB utilizes label
Externí odkaz:
http://arxiv.org/abs/2412.11408
Pedestrian trajectory prediction remains a challenge for autonomous systems, particularly due to the intricate dynamics of social interactions. Accurate forecasting requires a comprehensive understanding not only of each pedestrian's previous traject
Externí odkaz:
http://arxiv.org/abs/2412.04673
Self-driving research often underrepresents cyclist collisions and safety. To address this, we present CycleCrash, a novel dataset consisting of 3,000 dashcam videos with 436,347 frames that capture cyclists in a range of critical situations, from co
Externí odkaz:
http://arxiv.org/abs/2409.19942
Sleep is known to be a key factor in emotional regulation and overall mental health. In this study, we explore the integration of sleep measures from the previous night into wearable-based mood recognition. To this end, we propose NapTune, a novel pr
Externí odkaz:
http://arxiv.org/abs/2409.04723
Large language models (LLMs) have triggered a new stream of research focusing on compressing the context length to reduce the computational cost while ensuring the retention of helpful information for LLMs to answer the given question. Token-based re
Externí odkaz:
http://arxiv.org/abs/2409.01227
Autor:
Roy, Shuvendu, Parhizkar, Yasaman, Ogidi, Franklin, Khazaie, Vahid Reza, Colacci, Michael, Etemad, Ali, Dolatabadi, Elham, Afkanpour, Arash
We perform a comprehensive benchmarking of contrastive frameworks for learning multimodal representations in the medical domain. Through this study, we aim to answer the following research questions: (i) How transferable are general-domain representa
Externí odkaz:
http://arxiv.org/abs/2406.07450
Existing approaches for learning representations of time-series keep the temporal arrangement of the time-steps intact with the presumption that the original order is the most optimal for learning. However, non-adjacent sections of real-world time-se
Externí odkaz:
http://arxiv.org/abs/2405.20082
Autor:
Sarkar, Pritam, Ebrahimi, Sayna, Etemad, Ali, Beirami, Ahmad, Arık, Sercan Ö., Pfister, Tomas
Despite their significant advancements, Multimodal Large Language Models (MLLMs) often generate factually inaccurate information, referred to as hallucination. In this work, we address object hallucinations in MLLMs, where information is generated ab
Externí odkaz:
http://arxiv.org/abs/2405.18654
For the first time, we explore few-shot tuning of vision foundation models for class-incremental learning. Unlike existing few-shot class incremental learning (FSCIL) methods, which train an encoder on a base session to ensure forward compatibility f
Externí odkaz:
http://arxiv.org/abs/2405.16625
We address the problem of federated domain generalization in an unsupervised setting for the first time. We first theoretically establish a connection between domain shift and alignment of gradients in unsupervised federated learning and show that al
Externí odkaz:
http://arxiv.org/abs/2405.16304