Zobrazeno 1 - 10
of 119
pro vyhledávání: '"Karimi, Akbar"'
Autor:
Nie, Shangrui, Fromm, Michael, Welch, Charles, Görge, Rebekka, Karimi, Akbar, Plepi, Joan, Mowmita, Nazia Afsan, Flores-Herr, Nicolas, Ali, Mehdi, Flek, Lucie
While preliminary findings indicate that multilingual LLMs exhibit reduced bias compared to monolingual ones, a comprehensive understanding of the effect of multilingual training on bias mitigation, is lacking. This study addresses this gap by system
Externí odkaz:
http://arxiv.org/abs/2407.05740
Current state-of-the-art two-stage models on instance segmentation task suffer from several types of imbalances. In this paper, we address the Intersection over the Union (IoU) distribution imbalance of positive input Regions of Interest (RoIs) durin
Externí odkaz:
http://arxiv.org/abs/2404.16633
Autor:
Karimi, Akbar, Flek, Lucie
The class imbalance problem can cause machine learning models to produce an undesirable performance on the minority class as well as the whole dataset. Using data augmentation techniques to increase the number of samples is one way to tackle this pro
Externí odkaz:
http://arxiv.org/abs/2306.00346
Publikováno v:
International Conference on Image Analysis and Processing. Springer, Cham, 2022
Nowadays, Semi-Supervised Object Detection (SSOD) is a hot topic, since, while it is rather easy to collect images for creating a new dataset, labeling them is still an expensive and time-consuming task. One of the successful methods to take advantag
Externí odkaz:
http://arxiv.org/abs/2206.10186
This paper proposes AEDA (An Easier Data Augmentation) technique to help improve the performance on text classification tasks. AEDA includes only random insertion of punctuation marks into the original text. This is an easier technique to implement f
Externí odkaz:
http://arxiv.org/abs/2108.13230
Publikováno v:
International Conference on Computer Analysis of Images and Patterns. Springer, Cham, 2021
Within the field of instance segmentation, most of the state-of-the-art deep learning networks rely nowadays on cascade architectures, where multiple object detectors are trained sequentially, re-sampling the ground truth at each step. This offers a
Externí odkaz:
http://arxiv.org/abs/2104.01329
With the ever-increasing availability of digital information, toxic content is also on the rise. Therefore, the detection of this type of language is of paramount importance. We tackle this problem utilizing a combination of a state-of-the-art pre-tr
Externí odkaz:
http://arxiv.org/abs/2103.09645
Aspect-Based Sentiment Analysis (ABSA) studies the consumer opinion on the market products. It involves examining the type of sentiments as well as sentiment targets expressed in product reviews. Analyzing the language used in a review is a difficult
Externí odkaz:
http://arxiv.org/abs/2010.11731
Publikováno v:
International Conference on Pattern Recognition (ICPR). IEEE, 2021
Given the wide diffusion of deep neural network architectures for computer vision tasks, several new applications are nowadays more and more feasible. Among them, a particular attention has been recently given to instance segmentation, by exploiting
Externí odkaz:
http://arxiv.org/abs/2004.13665
This paper considers the task of matching images and sentences by learning a visual-textual embedding space for cross-modal retrieval. Finding such a space is a challenging task since the features and representations of text and image are not compara
Externí odkaz:
http://arxiv.org/abs/2002.10016