Thomas Mensink
I am a research scientist working on Computer Vision and Deep Learning.
Other research interests include: (learning) image representations, dense prediction tasks, zero-shot learning, metric learning and structured predictions all applied on image classification and retrieval tasks. My work has been awarded -among others- by the ECCV Koenderink Prize (2020), a NWO VENI Grant (2015), the ACM Multimedia Best Paper Award (2014), and the ACM ICMR Best Paper Award (2016).
For a full list of (pre-Google) publications see Google Scholar or personal website
Other research interests include: (learning) image representations, dense prediction tasks, zero-shot learning, metric learning and structured predictions all applied on image classification and retrieval tasks. My work has been awarded -among others- by the ECCV Koenderink Prize (2020), a NWO VENI Grant (2015), the ACM Multimedia Best Paper Award (2014), and the ACM ICMR Best Paper Award (2016).
For a full list of (pre-Google) publications see Google Scholar or personal website
Research Areas
Authored Publications
Sort By
Preview abstract
Mixup is a widely adopted strategy for training deep networks, where additional samples are augmented through a linear interpolation of input pairs and their corresponding labels. Mixup has shown to improve classification performance, network calibration, and out-of-distribution generalization. While effective, a cornerstone of Mixup, namely that networks learn linear behavior patterns between classes, is only indirectly enforced since the output interpolation is performed at the probability level. This paper seeks to address this limitation by instead mixing the classifiers of the labels directly for each mixed input pair. We propose to define the target of each augmented sample as a uniquely new classifier, whose parameters are given as a linear interpolation of the classifier vectors of the input sample pair. The space of all possible classifiers is continuous and spans all interpolations between classifier pairs. To perform tractable optimization, we propose a dual-contrastive Infinite Class Mixup loss, where we contrast the unique classifier of a single pair to both the mixed classifiers and the predicted outputs of all other pairs in a batch. Infinite Class Mixup is generic in nature and applies to any variant of Mixup. Empirically, we show that our formulation outperforms standard Mixup and variants such as RegMixup and Remix on balanced and long-tailed recognition benchmarks, both at large-scale and in data-constrained settings, highlighting the broad applicability of our approach.
View details
Scaling Vision Transformers to 22 Billion Parameters
Josip Djolonga
Basil Mustafa
Piotr Padlewski
Justin Gilmer
Mathilde Caron
Rodolphe Jenatton
Lucas Beyer
Michael Tschannen
Anurag Arnab
Carlos Riquelme
Gamaleldin Elsayed
Fisher Yu
Avital Oliver
Fantine Huot
Mark Collier
Vighnesh Birodkar
Yi Tay
Alexander Kolesnikov
Filip Pavetić
Thomas Kipf
Xiaohua Zhai
Neil Houlsby
Arxiv (2023)
Preview abstract
The scaling of Transformers has driven breakthrough capabilities for language models.
At present, the largest large language models (LLMs) contain upwards of 100B parameters.
Vision Transformers (ViT) have introduced the same architecture to image and video modeling, but these have not yet been successfully scaled to nearly the same degree; the largest dense ViT contains 4B parameters. We present a recipe for highly efficient training of a 22B-parameter ViT and perform a wide variety of experiments on the resulting model. When evaluated on downstream tasks (often with a lightweight linear model on frozen features) ViT22B demonstrates increasing performance with scale. We further observe other interesting benefits of scale, including an improved tradeoff between bias and performance, an improved alignment to human visual perception in terms of shape/texture bias, and improved robustness. ViT22B demonstrates the potential for "LLM-like'' scaling in vision, and provides key steps towards getting there.
View details
Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories
Lluis Castrejon
Arushi Goel
Felipe Cadar
Vittorio Ferrari
ICCV (2023)
Preview abstract
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 contains 221k unique question+answer pairs each matched with (up to) 5 images, resulting in a total of 1M VQA samples. Moreover, our dataset comes with a controlled knowledge base derived from Wikipedia, marking the evidence to support each answer. 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. Moreover, we experimentally show that progress on answering our encyclopedic questions can be achieved by augmenting large models with a mechanism that retrieves relevant information from the knowledge base. An oracle experiment with perfect retrieval achieves 87.0% accuracy on the single-hop portion of our dataset, and an automatic retrieval-augmented prototype yields 48.8%. We believe that our dataset enables future research on retrieval-augmented vision+language models. It is available at https://github.com/google-research/google-research/tree/master/encyclopedic_vqa.
View details
How (not) to ensemble LVLMs for VQA
Lisa Alazraki
Lluis Castrejon
Fantine Huot
"I Can't Believe It's Not Better: Failure Modes in the Age of Foundation Models" at NeurIPS 2023 Workshops
Preview abstract
This paper studies ensembling in the era of Large Vision-Language Models (LVLMs). Ensembling is a classical method to combine different models to get increased performance. In the recent work on Encyclopedic-VQA the authors examine a wide variety of models to solve their task: from vanilla LVLMs, to models including the caption as extra context, to models augmented with Lens-based retrieval of Wikipedia pages. Intuitively these models are highly complementary which should make them ideal for ensembling. Indeed, an oracle experiment shows potential gains from 48.8% accuracy (the best single model) all the way up to 67% (best possible ensemble). So it is a trivial exercise to create an ensemble with substantial real gains. Or is it?
View details
Transferability Estimation using Bhattacharyya Class Separability
Michal Pandy
Andrea Agostinelli
Vittorio Ferrari
CVPR (2022)
Preview abstract
Transfer learning has become a popular method for leveraging pre-trained models in computer vision. However, without performing computationally expensive fine-tuning, it is difficult to quantify which pre-trained source models are suitable for a specific target task, or, conversely, to which tasks a pre-trained source model can be easily adapted to. In this work, we propose Gaussian Bhattacharyya Coefficient (GBC), a novel method for quantifying transferability between a source model and a target dataset. In a first step we embed all target images in the feature space defined by the source model, and represent them with per-class Gaussians. 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. We evaluate GBC on image classification tasks in the context of dataset and architecture selection. Further, we also perform experiments on the more complex semantic segmentation transferability estimation task. We demonstrate that GBC outperforms state-of-the-art transferability metrics on most evaluation criteria in the semantic segmentation settings, matches the performance of top methods for dataset transferability in image classification, and performs best on architecture selection problems for image classification.
View details
How stable are Transferability Metrics evaluations?
Andrea Agostinelli
Michal Pandy
Vittorio Ferrari
ECCV (2022)
Preview abstract
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 finetuning them all. However, existing works rely on custom experimental setups which differ across papers, leading to inconsistent conclusions about which transferability metrics work best. In this paper we conduct
a large-scale study by systematically constructing a broad range of 715k experimental setup variations. We discover that even small variations to an experimental setup lead to different conclusions about the superiority of a transferability metric over another. Then we propose better evaluations by aggregating across many experiments, enabling to reach more stable conclusions. As a result, we reveal the superiority of LogME at selecting good source datasets to transfer from in a semantic segmentation scenario, and N LEEP at selecting good source architectures in an image classification scenario. However, no single transferability metric works best in all scenarios.
View details
Preview abstract
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. Since fine-tuning all possible ensembles is computationally prohibitive, we aim at predicting performance on the target dataset using a computationally efficient transferability metric. We propose several new transferability metrics designed for this task and evaluate them in a challenging and realistic transfer learning setup for semantic segmentation: we create a large and diverse pool of source models by considering 17 source datasets covering a wide variety of image domain, two different architectures, and two pre-training schemes. Given this pool, we then automatically select a subset to form an ensemble performing well on a given target dataset. We compare the ensemble selected by our method to two baselines which select a single source model, either (1) from the same pool as our method; or (2) from a pool containing large source models, each with similar capacity as an ensemble. Averaged over 17 target datasets, we outperform these baselines by 6.0% and 2.5% relative mean IoU, respectively.
View details
Preview abstract
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 classes, images following
a specific distribution, annotation protocols, etc. In this paper we explore the automatic discovery of visual-semantic relations between labels across datasets. We aim to understand how instances of a certain class in a dataset relate to the instances of another class in another dataset. Are they in an identity, parent/child, overlap relation? Or is there no link between them at all? To find relations between labels across datasets, we propose methods based on language, on vision, and on their combination. We show that we can effectively discover label relations across datasets, as well as their type. We apply our method to four applications: understand label relations, identify missing aspects, increase label specificity, and predict transfer learning gains. We conclude that label relations cannot be established by looking at the names of classes alone, as they depend strongly on how each of the datasets was constructed.
View details
Multi-Loss Weighting with Coefficient of Variations
Rick Groenendijk
Sezer Karaoglu
Theo Gevers
Winter Conference on Applications of Computer Vision (WACV) (2021)
Preview abstract
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 final performance is sensitive to choosing the correct (relative) weights for these losses. Finding a good set of weights is often done by adopting them into the set of hyper-parameters, which are set using an extensive grid search. This is computationally expensive. In this paper, the weights are defined based on properties observed while training the model, including the specific batch loss, the average loss, and the variance for each of the losses. An additional advantage is that the defined weights evolve during training, instead of using static loss weights. In literature, loss weighting is mostly used in a multi-task learning setting, where the different tasks obtain different weights. However, there is a plethora of single-task multi-loss problems that can benefit from automatic loss weighting. In this paper, it is shown that these multi-task approaches do not work on single tasks. Instead, a method is proposed that automatically and dynamically tunes loss weights throughout training specifically for single-task multi-loss problems. The method incorporates a measure of uncertainty to balance the losses. The validity of the approach is shown empirically for different tasks on multiple datasets.
View details
EDEN: Multimodal Synthetic Dataset of Enclosed Garden Scenes
Hoang-An Le
Partha Das
Sezer Karaoglu
Theo Gevers
Winter Conference on Applications of Computer Vision (WACV) (2021)
Preview abstract
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 in nature-centered scenes such as gardens or parks. To promote machine learning methods for nature-oriented applications, such as agriculture and gardening, we propose the multimodal synthetic dataset for Enclosed garDEN scenes (EDEN). The dataset features more than 300K images captured from more than 100 garden models. Each image is annotated with various low/high-level vision modalities, including semantic segmentation, depth, surface normals, intrinsic colors, and optical flow. Experimental results on the state-of-the-art methods for semantic segmentation and monocular depth prediction, two important tasks in computer vision, show positive impact of pre-training deep networks on our dataset for unstructured natural scenes. The dataset and related materials will be available at https://lhoangan.github.io/eden.
View details
