Zobrazeno 1 - 10
of 81
pro vyhledávání: '"Baktashmotlagh, Mahsa"'
Accurately estimating model performance poses a significant challenge, particularly in scenarios where the source and target domains follow different data distributions. Most existing performance prediction methods heavily rely on the source data in
Externí odkaz:
http://arxiv.org/abs/2408.02209
Autor:
Khramtsova, Ekaterina, Leelanupab, Teerapong, Zhuang, Shengyao, Baktashmotlagh, Mahsa, Zuccon, Guido
In this demo we present a web-based application for selecting an effective pre-trained dense retriever to use on a private collection. Our system, DenseQuest, provides unsupervised selection and ranking capabilities to predict the best dense retrieve
Externí odkaz:
http://arxiv.org/abs/2407.06685
Autor:
Lim, Jia Syuen, Chen, Zhuoxiao, Baktashmotlagh, Mahsa, Chen, Zhi, Yu, Xin, Huang, Zi, Luo, Yadan
Class-agnostic object detection (OD) can be a cornerstone or a bottleneck for many downstream vision tasks. Despite considerable advancements in bottom-up and multi-object discovery methods that leverage basic visual cues to identify salient objects,
Externí odkaz:
http://arxiv.org/abs/2406.14924
LiDAR-based 3D object detection is pivotal across many applications, yet the performance of such detection systems often degrades after deployment, especially when faced with unseen test point clouds originating from diverse locations or subjected to
Externí odkaz:
http://arxiv.org/abs/2406.14878
In this paper we present Large Language Model Assisted Retrieval Model Ranking (LARMOR), an effective unsupervised approach that leverages LLMs for selecting which dense retriever to use on a test corpus (target). Dense retriever selection is crucial
Externí odkaz:
http://arxiv.org/abs/2402.04853
Autor:
Michalkiewicz, Mateusz, Faraki, Masoud, Yu, Xiang, Chandraker, Manmohan, Baktashmotlagh, Mahsa
Overfitting to the source domain is a common issue in gradient-based training of deep neural networks. To compensate for the over-parameterized models, numerous regularization techniques have been introduced such as those based on dropout. While thes
Externí odkaz:
http://arxiv.org/abs/2310.07361
We propose the new problem of choosing which dense retrieval model to use when searching on a new collection for which no labels are available, i.e. in a zero-shot setting. Many dense retrieval models are readily available. Each model however is char
Externí odkaz:
http://arxiv.org/abs/2309.09403
Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection. While effective, existing DA methods suffer from a substantial drop in performance when applied
Externí odkaz:
http://arxiv.org/abs/2307.07944
Achieving a reliable LiDAR-based object detector in autonomous driving is paramount, but its success hinges on obtaining large amounts of precise 3D annotations. Active learning (AL) seeks to mitigate the annotation burden through algorithms that use
Externí odkaz:
http://arxiv.org/abs/2307.07942
To alleviate the high annotation cost in LiDAR-based 3D object detection, active learning is a promising solution that learns to select only a small portion of unlabeled data to annotate, without compromising model performance. Our empirical study, h
Externí odkaz:
http://arxiv.org/abs/2301.09249