Zobrazeno 1 - 10
of 56
pro vyhledávání: '"Georgescu, Mariana Iuliana"'
CLIP has shown impressive results in aligning images and texts at scale. However, its ability to capture detailed visual features remains limited because CLIP matches images and texts at a global level. To address this issue, we propose FLAIR, Fine-g
Externí odkaz:
http://arxiv.org/abs/2412.03561
Vision-Language Models (VLMs) trained with contrastive loss have achieved significant advancements in various vision and language tasks. However, the global nature of contrastive loss makes VLMs focus predominantly on foreground objects, neglecting o
Externí odkaz:
http://arxiv.org/abs/2412.01814
In Composed Video Retrieval, a video and a textual description which modifies the video content are provided as inputs to the model. The aim is to retrieve the relevant video with the modified content from a database of videos. In this challenging ta
Externí odkaz:
http://arxiv.org/abs/2407.16658
Autor:
Grigore, Diana-Nicoleta, Georgescu, Mariana-Iuliana, Justo, Jon Alvarez, Johansen, Tor, Ionescu, Andreea Iuliana, Ionescu, Radu Tudor
Few-shot knowledge distillation recently emerged as a viable approach to harness the knowledge of large-scale pre-trained models, using limited data and computational resources. In this paper, we propose a novel few-shot feature distillation approach
Externí odkaz:
http://arxiv.org/abs/2404.09326
Autor:
Justo, Jon Alvarez, Ghita, Alexandru, Kovac, Daniel, Garrett, Joseph L., Georgescu, Mariana-Iuliana, Gonzalez-Llorente, Jesus, Ionescu, Radu Tudor, Johansen, Tor Arne
Satellites are increasingly adopting on-board AI to optimize operations and increase autonomy through in-orbit inference. The use of Deep Learning (DL) models for segmentation in hyperspectral imagery offers advantages for remote sensing applications
Externí odkaz:
http://arxiv.org/abs/2310.16210
Learning Using Privileged Information is a particular type of knowledge distillation where the teacher model benefits from an additional data representation during training, called privileged information, improving the student model, which does not s
Externí odkaz:
http://arxiv.org/abs/2309.15238
Autor:
Georgescu, Mariana-Iuliana
Pathological anomalies exhibit diverse appearances in medical imaging, making it difficult to collect and annotate a representative amount of data required to train deep learning models in a supervised setting. Therefore, in this work, we tackle anom
Externí odkaz:
http://arxiv.org/abs/2307.07534
Autor:
Georgescu, Mariana-Iuliana, Fonseca, Eduardo, Ionescu, Radu Tudor, Lucic, Mario, Schmid, Cordelia, Arnab, Anurag
Can we leverage the audiovisual information already present in video to improve self-supervised representation learning? To answer this question, we study various pretraining architectures and objectives within the masked autoencoding framework, moti
Externí odkaz:
http://arxiv.org/abs/2212.05922
Medical image segmentation is an actively studied task in medical imaging, where the precision of the annotations is of utter importance towards accurate diagnosis and treatment. In recent years, the task has been approached with various deep learnin
Externí odkaz:
http://arxiv.org/abs/2210.12388
Autor:
Barbalau, Antonio, Ionescu, Radu Tudor, Georgescu, Mariana-Iuliana, Dueholm, Jacob, Ramachandra, Bharathkumar, Nasrollahi, Kamal, Khan, Fahad Shahbaz, Moeslund, Thomas B., Shah, Mubarak
A self-supervised multi-task learning (SSMTL) framework for video anomaly detection was recently introduced in literature. Due to its highly accurate results, the method attracted the attention of many researchers. In this work, we revisit the self-s
Externí odkaz:
http://arxiv.org/abs/2207.08003