Pascal Mettes

Pascal Mettes

Auto-generated profile, based on publicly available information

Pascal Mettes

University of Amsterdam

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 March 2024 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
PMPascal Mettes
Pascal Mettes
MAMina Ghadimi Atigh
Mina Ghadimi Atigh
MKMartin Keller-Ressel
Martin Keller-Ressel
JGJeffrey Gu
Jeffrey Gu
SYSerena Yeung
Serena Yeung
Deep representation learning is a ubiquitous part of modern computer vision. While Euclidean space has been the de facto standard manifold for learning visual representations, hyperbolic space has recently gained rapid traction for learning in computer vision. Specifically, hyperbolic learning has shown a strong potential to embed hierarchical structures, learn from limited samples, quantify uncertainty, add robustness, limit error severity, and more. In this paper, we provide a categorization and in-depth overview of current literature on hyperbolic learning for computer vision. We research both supervised and unsupervised literature and identify three main research themes in each direction. We outline how hyperbolic learning is performed in all themes and discuss the main research problems that benefit from current advances in hyperbolic learning for computer vision. Moreover, we provide a high-level intuition behind hyperbolic geometry and outline open research questions to further advance research in this direction.

11 February 2022 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
ZSZenglin Shi
Zenglin Shi
PMPascal Mettes
Pascal Mettes
SMSubhransu Maji
Subhransu Maji
CSCees G. M. Snoek
Cees G. M. Snoek
The deep image prior showed that a randomly initialized network with a suitable architecture can be trained to solve inverse imaging problems by simply optimizing it’s parameters to reconstruct a single degraded image. However, it suffers from two practical limitations. First, it remains unclear how to control the prior beyond the choice of the network architecture. Second, training requires an oracle stopping criterion as during the optimization the performance degrades after reaching an optimum value. To address these challenges we introduce a frequency-band correspondence measure to characterize the spectral bias of the deep image prior, where low-frequency image signals are learned faster and better than high-frequency counterparts. Based on our observations, we propose techniques to prevent the eventual performance degradation and accelerate convergence. We introduce a Lipschitz-controlled convolution layer and a Gaussian-controlled upsampling layer as plug-in replacements for layers used in the deep architectures. The experiments show that with these changes the performance does not degrade during optimization, relieving us from the need for an oracle stopping criterion. We further outline a stopping criterion to avoid superfluous computation. Finally, we show that our approach obtains favorable results compared to current approaches across various denoising, deblocking, inpainting, super-resolution and detail enhancement tasks. Code is available at https://github.com/shizenglin/Measure-and-Control-Spectral-Bias.

16 September 2016
Verified
Book Chapter
Closed access
PDF file
PMPascal Mettes
Pascal Mettes
JGJan C. van Gemert
Jan C. van Gemert
CSCees G. M. Snoek
Cees G. M. Snoek

19 March 2015
Verified
Book Chapter
Closed access
PDF file
JGJan C. van Gemert
Jan C. van Gemert
CVCamiel R. Verschoor
Camiel R. Verschoor
PMPascal Mettes
Pascal Mettes
KEKitso Epema
Kitso Epema
LKLian Pin Koh
Lian Pin Koh
Serge WichSerge Wich
Serge Wich

22 May 2020 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
PMPascal Mettes
Pascal Mettes
DKDennis C. Koelma
Dennis C. Koelma
CSCees G. M. Snoek
Cees G. M. Snoek
This article aims for the detection and search of events in videos, where video examples are either scarce or even absent during training. To enable such event detection and search, ImageNet concept banks have shown to be effective. Rather than employing the standard concept bank of 1,000 ImageNet classes, we leverage the full 21,841-class dataset. We identify two problems with using the full dataset: (i) there is an imbalance between the number of examples per concept, and (ii) not all concepts are equally relevant for events. In this article, we propose to balance large-scale image hierarchies for pre-training. We shuffle concepts based on bottom-up and top-down operations to overcome the problems of example imbalance and concept relevance. Using this strategy, we arrive at the shuffled ImageNet bank, a concept bank with an order of magnitude more concepts compared to standard ImageNet banks. Compared to standard ImageNet pre-training, our shuffles result in more discriminative representations to train event models from the limited video event examples. For event search, the broad range of concepts enable a closer match between textual queries of events and concept detections in videos. Experimentally, we show the benefit of the proposed bank for event detection and event search, with state-of-the-art performance for both tasks on the challenging TRECVID Multimedia Event Detection and Ad-Hoc Video Search benchmarks.

9 February 2024 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
ZSZenglin Shi
Zenglin Shi
PMPascal Mettes
Pascal Mettes
CSCees G. M. Snoek
Cees G. M. Snoek