no code implementations • 8 Apr 2024 • Lluis Castrejon, Thomas Mensink, Howard Zhou, Vittorio Ferrari, Andre Araujo, Jasper Uijlings
We start from a multimodal ReAct-based system and make it hierarchical by enabling our HAMMR agents to call upon other specialized agents.
no code implementations • 10 Oct 2023 • Lisa Alazraki, Lluis Castrejon, Mostafa Dehghani, Fantine Huot, Jasper Uijlings, Thomas Mensink
So it is a trivial exercise to create an ensemble with substantial real gains.
1 code implementation • ICCV 2023 • Thomas Mensink, Jasper Uijlings, Lluis Castrejon, Arushi Goel, Felipe Cadar, Howard Zhou, Fei Sha, André Araujo, Vittorio Ferrari
Empirically, we show that our dataset poses a hard challenge for large vision+language models as they perform poorly on our dataset: PaLI [14] is state-of-the-art on OK-VQA [37], yet it only achieves 13. 0% accuracy on our dataset.
no code implementations • 9 Jun 2022 • Jasper Uijlings, Thomas Mensink, Vittorio Ferrari
To find relations between labels across datasets, we propose methods based on language, on vision, and on their combination.
no code implementations • 4 Apr 2022 • Andrea Agostinelli, Michal Pándy, Jasper Uijlings, Thomas Mensink, Vittorio Ferrari
Transferability metrics is a maturing field with increasing interest, which aims at providing heuristics for selecting the most suitable source models to transfer to a given target dataset, without fine-tuning them all.
no code implementations • CVPR 2022 • Andrea Agostinelli, Jasper Uijlings, Thomas Mensink, Vittorio Ferrari
We address the problem of ensemble selection in transfer learning: Given a large pool of source models we want to select an ensemble of models which, after fine-tuning on the target training set, yields the best performance on the target test set.
no code implementations • CVPR 2022 • Michal Pándy, Andrea Agostinelli, Jasper Uijlings, Vittorio Ferrari, Thomas Mensink
Then, we estimate their pairwise class separability using the Bhattacharyya coefficient, yielding a simple and effective measure of how well the source model transfers to the target task.
no code implementations • 24 Mar 2021 • Thomas Mensink, Jasper Uijlings, Alina Kuznetsova, Michael Gygli, Vittorio Ferrari
Our study leads to several insights and concrete recommendations: (1) for most tasks there exists a source which significantly outperforms ILSVRC'12 pre-training; (2) the image domain is the most important factor for achieving positive transfer; (3) the source dataset should \emph{include} the image domain of the target dataset to achieve best results; (4) at the same time, we observe only small negative effects when the image domain of the source task is much broader than that of the target; (5) transfer across task types can be beneficial, but its success is heavily dependent on both the source and target task types.
no code implementations • 8 Apr 2020 • Michael Gygli, Jasper Uijlings, Vittorio Ferrari
This paper proposes to make a first step towards compatible and hence reusable network components.
1 code implementation • ECCV 2020 • Jordi Pont-Tuset, Jasper Uijlings, Soravit Changpinyo, Radu Soricut, Vittorio Ferrari
We ask annotators to describe an image with their voice while simultaneously hovering their mouse over the region they are describing.
Ranked #2 on Image Captioning on Localized Narratives
no code implementations • ECCV 2020 • Theodora Kontogianni, Michael Gygli, Jasper Uijlings, Vittorio Ferrari
Our approach enables the adaptation to a particular object and its background, to distributions shifts in a test set, to specific object classes, and even to large domain changes, where the imaging modality changes between training and testing.
Ranked #1 on Interactive Segmentation on DRIONS-DB
1 code implementation • 2 Nov 2018 • Alina Kuznetsova, Hassan Rom, Neil Alldrin, Jasper Uijlings, Ivan Krasin, Jordi Pont-Tuset, Shahab Kamali, Stefan Popov, Matteo Malloci, Alexander Kolesnikov, Tom Duerig, Vittorio Ferrari
We present Open Images V4, a dataset of 9. 2M images with unified annotations for image classification, object detection and visual relationship detection.
1 code implementation • CVPR 2018 • Ksenia Konyushkova, Jasper Uijlings, Christoph Lampert, Vittorio Ferrari
We demonstrate that (1) our agents are able to learn efficient annotation strategies in several scenarios, automatically adapting to the image difficulty, the desired quality of the boxes, and the detector strength; (2) in all scenarios the resulting annotation dialogs speed up annotation compared to manual box drawing alone and box verification alone, while also outperforming any fixed combination of verification and drawing in most scenarios; (3) in a realistic scenario where the detector is iteratively re-trained, our agents evolve a series of strategies that reflect the shifting trade-off between verification and drawing as the detector grows stronger.
no code implementations • CVPR 2018 • Jasper Uijlings, Stefan Popov, Vittorio Ferrari
We propose to revisit knowledge transfer for training object detectors on target classes from weakly supervised training images, helped by a set of source classes with bounding-box annotations.
1 code implementation • 18 Jul 2017 • Zbigniew Wojna, Vittorio Ferrari, Sergio Guadarrama, Nathan Silberman, Liang-Chieh Chen, Alireza Fathi, Jasper Uijlings
Many machine vision applications, such as semantic segmentation and depth prediction, require predictions for every pixel of the input image.
10 code implementations • CVPR 2018 • Holger Caesar, Jasper Uijlings, Vittorio Ferrari
To understand stuff and things in context we introduce COCO-Stuff, which augments all 164K images of the COCO 2017 dataset with pixel-wise annotations for 91 stuff classes.
Ranked #1 on Semantic Segmentation on COCO-Stuff
1 code implementation • 26 Jul 2016 • Holger Caesar, Jasper Uijlings, Vittorio Ferrari
We propose a novel method for semantic segmentation, the task of labeling each pixel in an image with a semantic class.
Ranked #1 on Semantic Segmentation on SIFT-flow
no code implementations • 6 Jul 2015 • Holger Caesar, Jasper Uijlings, Vittorio Ferrari
Semantic segmentation is the task of assigning a class-label to each pixel in an image.
Ranked #2 on Semantic Segmentation on SIFT-flow
no code implementations • CVPR 2015 • Jasper Uijlings, Vittorio Ferrari
Intuitively, the appearance of true object boundaries varies from image to image.
no code implementations • CVPR 2014 • Victoria Yanulevskaya, Jasper Uijlings, Nicu Sebe
It has been shown that such object regions can be used to focus computer vision techniques on the parts of an image that matter most leading to significant improvements in both object localisation and semantic segmentation in recent years.