5 papers
Revisiting [CLS] and Patch Token Interaction in Vision Transformers
Alexis Marouani, Oriane Siméoni, Hervé Jégou +2
Vision Transformers have emerged as powerful, scalable and versatile representation learners. To capture both global and local features, a learnable [CLS] class token is typically…
DINOv3
Oriane Siméoni, Huy V. Vo, Maximilian Seitzer +23
Self-supervised learning holds the promise of eliminating the need for manual data annotation, enabling models to scale effortlessly to massive datasets and larger architectures. B…
Test-time Contrastive Concepts for Open-world Semantic Segmentation with Vision-Language Models
Monika WysoczaÅska, Antonin Vobecky, Amaia Cardiel +4
Recent CLIP-like Vision-Language Models (VLMs), pre-trained on large amounts of image-text pairs to align both modalities with a simple contrastive objective, have paved the way to…
LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension
Amaia Cardiel, Eloi Zablocki, Elias Ramzi +2
Vision Language Models (VLMs) have demonstrated remarkable capabilities in various open-vocabulary tasks, yet their zero-shot performance lags behind task-specific fine-tuned model…
DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment
Cijo Jose, Théo Moutakanni, Dahyun Kang +11
Self-supervised visual foundation models produce powerful embeddings that achieve remarkable performance on a wide range of downstream tasks. However, unlike vision-language models…