118 citations · 258 across the 21 of their papers we have counts for
24 papers
Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories
Thomas Mensink, Jasper Uijlings, Lluis Castrejon +6
We propose Encyclopedic-VQA, a large scale visual question answering (VQA) dataset featuring visual questions about detailed properties of fine-grained categories and instances. It…
Infinite Class Mixup
Thomas Mensink, Pascal Mettes
Mixup is a widely adopted strategy for training deep networks, where additional samples are augmented by interpolating inputs and labels of training pairs. Mixup has shown to impro…
Scaling Vision Transformers to 22 Billion Parameters
Mostafa Dehghani, Josip Djolonga, Basil Mustafa +39
The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Visio…
The Missing Link: Finding label relations across datasets
Jasper Uijlings, Thomas Mensink, Vittorio Ferrari
Computer vision is driven by the many datasets available for training or evaluating novel methods. However, each dataset has a different set of class labels, visual definition of c…
How stable are Transferability Metrics evaluations?
Andrea Agostinelli, Michal Pándy, Jasper Uijlings +2
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…
Transferability Metrics for Selecting Source Model Ensembles
Andrea Agostinelli, Jasper Uijlings, Thomas Mensink +1
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 targe…
Transferability Estimation using Bhattacharyya Class Separability
Michal Pándy, Andrea Agostinelli, Jasper Uijlings +2
Transfer learning has become a popular method for leveraging pre-trained models in computer vision. However, without performing computationally expensive fine-tuning, it is difficu…
Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types
Thomas Mensink, Jasper Uijlings, Alina Kuznetsova +2
Transfer learning enables to re-use knowledge learned on a source task to help learning a target task. A simple form of transfer learning is common in current state-of-the-art comp…
EDEN: Multimodal Synthetic Dataset of Enclosed GarDEN Scenes
Hoang-An Le, Thomas Mensink, Partha Das +2
Multimodal large-scale datasets for outdoor scenes are mostly designed for urban driving problems. The scenes are highly structured and semantically different from scenarios seen i…
Novel View Synthesis from Single Images via Point Cloud Transformation
Hoang-An Le, Thomas Mensink, Partha Das +1
In this paper the argument is made that for true novel view synthesis of objects, where the object can be synthesized from any viewpoint, an explicit 3D shape representation isdesi…
Multi-Loss Weighting with Coefficient of Variations
Rick Groenendijk, Sezer Karaoglu, Theo Gevers +1
Many interesting tasks in machine learning and computer vision are learned by optimising an objective function defined as a weighted linear combination of multiple losses. The fina…
PointMixup: Augmentation for Point Clouds
Yunlu Chen, Vincent Tao Hu, Efstratios Gavves +4
This paper introduces data augmentation for point clouds by interpolation between examples. Data augmentation by interpolation has shown to be a simple and effective approach in th…
Post-hoc Calibration of Neural Networks by g-Layers
Amir Rahimi, Thomas Mensink, Kartik Gupta +3
Calibration of neural networks is a critical aspect to consider when incorporating machine learning models in real-world decision-making systems where the confidence of decisions a…
Calibration of Neural Networks using Splines
Kartik Gupta, Amir Rahimi, Thalaiyasingam Ajanthan +3
Calibrating neural networks is of utmost importance when employing them in safety-critical applications where the downstream decision making depends on the predicted probabilities.…
Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection
Alex Bewley, Pei Sun, Thomas Mensink +2
This paper presents a novel 3D object detection framework that processes LiDAR data directly on its native representation: range images. Benefiting from the compactness of range im…
On the Benefit of Adversarial Training for Monocular Depth Estimation
Rick Groenendijk, Sezer Karaoglu, Theo Gevers +1
In this paper we address the benefit of adding adversarial training to the task of monocular depth estimation. A model can be trained in a self-supervised setting on stereo pairs o…
3D Neighborhood Convolution: Learning Depth-Aware Features for RGB-D and RGB Semantic Segmentation
Yunlu Chen, Thomas Mensink, Efstratios Gavves
A key challenge for RGB-D segmentation is how to effectively incorporate 3D geometric information from the depth channel into 2D appearance features. We propose to model the effect…
Three for one and one for three: Flow, Segmentation, and Surface Normals
Hoang-An Le, Anil S. Baslamisli, Thomas Mensink +1
Optical flow, semantic segmentation, and surface normals represent different information modalities, yet together they bring better cues for scene understanding problems. In this p…
IterGANs: Iterative GANs to Learn and Control 3D Object Transformation
Ysbrand Galama, Thomas Mensink
We are interested in learning visual representations which allow for 3D manipulations of visual objects based on a single 2D image. We cast this into an image-to-image transformati…
Video Stream Retrieval of Unseen Queries using Semantic Memory
Spencer Cappallo, Thomas Mensink, Cees G. M. Snoek
Retrieval of live, user-broadcast video streams is an under-addressed and increasingly relevant challenge. The on-line nature of the problem requires temporal evaluation and the un…
Online Open World Recognition
Rocco De Rosa, Thomas Mensink, Barbara Caputo
As we enter into the big data age and an avalanche of images have become readily available, recognition systems face the need to move from close, lab settings where the number of c…
VideoStory Embeddings Recognize Events when Examples are Scarce
Amirhossein Habibian, Thomas Mensink, Cees G. M. Snoek
This paper aims for event recognition when video examples are scarce or even completely absent. The key in such a challenging setting is a semantic video representation. Rather tha…
Objects2action: Classifying and localizing actions without any video example
Mihir Jain, Jan C. van Gemert, Thomas Mensink +1
The goal of this paper is to recognize actions in video without the need for examples. Different from traditional zero-shot approaches we do not demand the design and specification…
Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks
Efstratios Gavves, Thomas Mensink, Tatiana Tommasi +2
How can we reuse existing knowledge, in the form of available datasets, when solving a new and apparently unrelated target task from a set of unlabeled data? In this work we make a…