1.1k citations · 1.7k across the 16 of their papers we have counts for
18 papers
Scalable Patch-Level Self-Supervised Learning
Maximilian Seitzer, Gabriele Trivigno, Antonín Vobecký +5
Self-supervised learning (SSL) at scale produces powerful visual representations. However, most scalable SSL methods rely on ad hoc combinations of multiple objectives and stabiliz…
Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Have
Elouan Gardès, Seung Eun Yi, Kartik Ahuja +6
We propose a label-free approach to adapt powerful but generic vision foundation models to specialized scientific domains. Standard supervised fine-tuning is often ill-suited to th…
Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images
Joséphine Raugel, Maximilian Seitzer, Marc Szafraniec +6
Backpropagation is the core learning mechanism underlying deep learning. However, whether and how this algorithm is implemented in the brain remains highly debated. In particular,…
CHMv2: Improvements in Global Canopy Height Mapping using DINOv3
John Brandt, Seungeun Yi, Jamie Tolan +9
Accurate canopy height information is essential for quantifying forest carbon, monitoring restoration and degradation, and assessing habitat structure, yet high-fidelity measuremen…
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…
Disentangling the Factors of Convergence between Brains and Computer Vision Models
Joséphine Raugel, Marc Szafraniec, Huy V. Vo +5
Many AI models trained on natural images develop representations that resemble those of the human brain. However, the factors that drive this brain-model similarity remain poorly u…
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…
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…
Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach
Huy V. Vo, Vasil Khalidov, Timothée Darcet +10
Self-supervised features are the cornerstone of modern machine learning systems. They are typically pre-trained on data collections whose construction and curation typically requir…
Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar
Jamie Tolan, Hung-I Yang, Ben Nosarzewski +13
Vegetation structure mapping is critical for understanding the global carbon cycle and monitoring nature-based approaches to climate adaptation and mitigation. Repeated measurement…
DINOv2: Learning Robust Visual Features without Supervision
Maxime Oquab, Timothée Darcet, Théo Moutakanni +23
The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. Thes…
Automatic Infectious Disease Classification Analysis with Concept Discovery
Elena Sizikova, Joshua Vendrow, Xu Cao +13
Automatic infectious disease classification from images can facilitate needed medical diagnoses. Such an approach can identify diseases, like tuberculosis, which remain under-diagn…
Active Learning Strategies for Weakly-supervised Object Detection
Huy V. Vo, Oriane Siméoni, Spyros Gidaris +3
Object detectors trained with weak annotations are affordable alternatives to fully-supervised counterparts. However, there is still a significant performance gap between them. We…
Localizing Objects with Self-Supervised Transformers and no Labels
Oriane Siméoni, Gilles Puy, Huy V. Vo +6
Localizing objects in image collections without supervision can help to avoid expensive annotation campaigns. We propose a simple approach to this problem, that leverages the activ…
Large-Scale Unsupervised Object Discovery
Huy V. Vo, Elena Sizikova, Cordelia Schmid +2
Existing approaches to unsupervised object discovery (UOD) do not scale up to large datasets without approximations that compromise their performance. We propose a novel formulatio…
Toward unsupervised, multi-object discovery in large-scale image collections
Huy V. Vo, Patrick Pérez, Jean Ponce
This paper addresses the problem of discovering the objects present in a collection of images without any supervision. We build on the optimization approach of Vo et al. (CVPR'19)…
Unsupervised Image Matching and Object Discovery as Optimization
Huy V. Vo, Francis Bach, Minsu Cho +4
The paper reformulates unsupervised object category discovery and image matching as a formal optimization problem and demonstrates its effectiveness on benchmark datasets.
Structural inpainting
Huy V. Vo, Ngoc Q. K. Duong, Patrick Perez
Scene-agnostic visual inpainting remains very challenging despite progress in patch-based methods. Recently, Pathak et al. 2016 have introduced convolutional "context encoders" (CE…