99 citations
- Université Paris CitéFR21 papers
- Sorbonne Paris CitéFR10 papers
- LIP6FR9 papers
- Délégation Paris 5FR5 papers
- University of Maryland, Baltimore CountyUS3 papers
- CEA Paris-SaclayFR2 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR2 papers
- Électricité de France (France)FR2 papers
- Google (United States)US2 papers
- Institut de Recherche en Informatique de ToulouseFR2 papers
- Institut Polytechnique de BordeauxFR2 papers
- Université Toulouse-I-CapitoleFR2 papers
4 papers · 1 filter
Interpret, prune and distill Donut : towards lightweight VLMs for VQA on document
Adnan Ben Mansour, Ayoub Karine, David Naccache
Recent advances in Visually-rich Document Understanding rely on large Vision-Language Models like Donut, which perform document-level Visual Question Answering without Optical Char…
Can SAR improve RSVQA performance?
Lucrezia Tosato, Sylvain Lobry, Flora Weissgerber +1
Remote sensing visual question answering (RSVQA) has been involved in several research in recent years, leading to an increase in new methods. RSVQA automatically extracts informat…
I2CKD : Intra- and Inter-Class Knowledge Distillation for Semantic Segmentation
Ayoub Karine, Thibault Napoléon, Maher Jridi
This paper proposes a new knowledge distillation method tailored for image semantic segmentation, termed Intra- and Inter-Class Knowledge Distillation (I2CKD). The focus of this me…
Learning an Adaptation Function to Assess Image Visual Similarities
Olivier Risser-Maroix, Amine Marzouki, Hala Djeghim +2
Human perception is routinely assessing the similarity between images, both for decision making and creative thinking. But the underlying cognitive process is not really well under…