Search Results - "Caron, Mathilde"

Unsupervised Pre-Training of Image Features on Non-Curated Data by Caron, Mathilde, Bojanowski, Piotr, Mairal, Julien, Joulin, Armand

“…Pre-training general-purpose visual features with convolutional neural networks without relying on annotations is a challenging and important task. Most recent…”
Get full text

ResMLP: Feedforward Networks for Image Classification With Data-Efficient Training by Touvron, Hugo, Bojanowski, Piotr, Caron, Mathilde, Cord, Matthieu, El-Nouby, Alaaeldin, Grave, Edouard, Izacard, Gautier, Joulin, Armand, Synnaeve, Gabriel, Verbeek, Jakob, Jegou, Herve

“…We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification. It is a simple residual network that alternates (i) a…”
Get full text

Emerging Properties in Self-Supervised Vision Transformers by Caron, Mathilde, Touvron, Hugo, Misra, Ishan, Jegou, Herve, Mairal, Julien, Bojanowski, Piotr, Joulin, Armand

“…In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) [16] that stand out compared to convolutional…”
Get full text

Location-Aware Self-Supervised Transformers for Semantic Segmentation by Caron, Mathilde, Houlsby, Neil, Schmid, Cordelia

“…Pixel-level labels are particularly expensive to acquire. Hence, pretraining is a critical step to improve models on a task like semantic segmentation…”
Get full text

Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples by Assran, Mahmoud, Caron, Mathilde, Misra, Ishan, Bojanowski, Piotr, Joulin, Armand, Ballas, Nicolas, Rabbat, Michael

“…This paper proposes a novel method of learning by predicting view assignments with support samples (PAWS). The method trains a model to minimize a consistency…”
Get full text

FlexiViT: One Model for All Patch Sizes by Beyer, Lucas, Izmailov, Pavel, Kolesnikov, Alexander, Caron, Mathilde, Kornblith, Simon, Zhai, Xiaohua, Minderer, Matthias, Tschannen, Michael, Alabdulmohsin, Ibrahim, Pavetic, Filip

“…Vision Transformers convert images to sequences by slicing them into patches. The size of these patches controls a speed/accuracy tradeoff, with smaller…”
Get full text

Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach by Caron, Mathilde, Fathi, Alireza, Schmid, Cordelia, Iscen, Ahmet

“…Web-scale visual entity recognition, the task of associating images with their corresponding entities within vast knowledge bases like Wikipedia, presents…”
Get full text

Self-Masking Networks for Unsupervised Adaptation by Warmerdam, Alfonso Taboada, Caron, Mathilde, Asano, Yuki M

“…With the advent of billion-parameter foundation models, efficient fine-tuning has become increasingly important for the adaptation of models to downstream…”
Get full text

Location-Aware Self-Supervised Transformers for Semantic Segmentation by Caron, Mathilde, Houlsby, Neil, Schmid, Cordelia

“…Pixel-level labels are particularly expensive to acquire. Hence, pretraining is a critical step to improve models on a task like semantic segmentation…”
Get full text

A Generative Approach for Wikipedia-Scale Visual Entity Recognition by Caron, Mathilde, Iscen, Ahmet, Fathi, Alireza, Schmid, Cordelia

“…In this paper, we address web-scale visual entity recognition, specifically the task of mapping a given query image to one of the 6 million existing entities…”
Get full text

A Generative Approach for Wikipedia-Scale Visual Entity Recognition by Caron, Mathilde, Iscen, Ahmet, Fathi, Alireza, Schmid, Cordelia

“…In this paper, we address web-scale visual entity recognition, specifically the task of mapping a given query image to one of the 6 million existing entities…”
Get full text

Retrieval-Enhanced Contrastive Vision-Text Models by Iscen, Ahmet, Caron, Mathilde, Fathi, Alireza, Schmid, Cordelia

“…Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts,…”
Get full text

Verbs in Action: Improving verb understanding in video-language models by Momeni, Liliane, Caron, Mathilde, Nagrani, Arsha, Zisserman, Andrew, Schmid, Cordelia

“…Understanding verbs is crucial to modelling how people and objects interact with each other and the environment through space and time. Recently,…”
Get full text

A Memory Transformer Network for Incremental Learning by Iscen, Ahmet, Bird, Thomas, Caron, Mathilde, Fathi, Alireza, Schmid, Cordelia

“…We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the…”
Get full text

Guided Diffusion from Self-Supervised Diffusion Features by Hu, Vincent Tao, Chen, Yunlu, Caron, Mathilde, Asano, Yuki M, Snoek, Cees G. M, Ommer, Bjorn

“…Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or classifier pretraining…”
Get full text

Weakly-Supervised Surgical Phase Recognition by Hirsch, Roy, Cohen, Regev, Caron, Mathilde, Golany, Tomer, Freedman, Daniel, Rivlin, Ehud

“…A key element of computer-assisted surgery systems is phase recognition of surgical videos. Existing phase recognition algorithms require frame-wise annotation…”
Get full text

Self-Supervised Learning for Endoscopic Video Analysis by Hirsch, Roy, Caron, Mathilde, Cohen, Regev, Livne, Amir, Shapiro, Ron, Golany, Tomer, Goldenberg, Roman, Freedman, Daniel, Rivlin, Ehud

“…MICCAI 2023 Self-supervised learning (SSL) has led to important breakthroughs in computer vision by allowing learning from large amounts of unlabeled data. As…”
Get full text

Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision by Goyal, Priya, Duval, Quentin, Seessel, Isaac, Caron, Mathilde, Misra, Ishan, Sagun, Levent, Joulin, Armand, Bojanowski, Piotr

“…Discriminative self-supervised learning allows training models on any random group of internet images, and possibly recover salient information that helps…”
Get full text

FlexiViT: One Model for All Patch Sizes by Beyer, Lucas, Izmailov, Pavel, Kolesnikov, Alexander, Caron, Mathilde, Kornblith, Simon, Zhai, Xiaohua, Minderer, Matthias, Tschannen, Michael, Alabdulmohsin, Ibrahim, Pavetic, Filip

“…Vision Transformers convert images to sequences by slicing them into patches. The size of these patches controls a speed/accuracy tradeoff, with smaller…”
Get full text

Unsupervised Dense Information Retrieval with Contrastive Learning by Izacard, Gautier, Caron, Mathilde, Hosseini, Lucas, Riedel, Sebastian, Bojanowski, Piotr, Joulin, Armand, Grave, Edouard

“…Recently, information retrieval has seen the emergence of dense retrievers, using neural networks, as an alternative to classical sparse methods based on…”
Get full text