11 citations · 16 across the 11 of their papers we have counts for
13 papers
Data-Efficient Challenges in Visual Inductive Priors: A Retrospective
Robert-Jan Bruintjes, Attila Lengyel, Osman Semih Kayhan +4
Deep Learning requires large amounts of data to train models that work well. In data-deficient settings, performance can be degraded. We investigate which Deep Learning methods ben…
VIPriors 4: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
Robert-Jan Bruintjes, Attila Lengyel, Marcos Baptista Rios +4
The fourth edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" workshop features two data-impaired challenges. These challenges address the problem…
Color Equivariant Convolutional Networks
Attila Lengyel, Ombretta Strafforello, Robert-Jan Bruintjes +2
Color is a crucial visual cue readily exploited by Convolutional Neural Networks (CNNs) for object recognition. However, CNNs struggle if there is data imbalance between color vari…
Benchmarking Data Efficiency and Computational Efficiency of Temporal Action Localization Models
Jan Warchocki, Teodor Oprescu, Yunhan Wang +6
In temporal action localization, given an input video, the goal is to predict which actions it contains, where they begin, and where they end. Training and testing current state-of…
Using and Abusing Equivariance
Tom Edixhoven, Attila Lengyel, Jan van Gemert
In this paper we show how Group Equivariant Convolutional Neural Networks use subsampling to learn to break equivariance to their symmetries. We focus on 2D rotations and reflectio…
VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
Robert-Jan Bruintjes, Attila Lengyel, Marcos Baptista Rios +4
The third edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" workshop featured four data-impaired challenges, focusing on addressing the limitation…
Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene Segmentation
Liang Zeng, Attila Lengyel, Nergis Tömen +1
In this work, we leverage estimated depth to boost self-supervised contrastive learning for segmentation of urban scenes, where unlabeled videos are readily available for training…
VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
Attila Lengyel, Robert-Jan Bruintjes, Marcos Baptista Rios +4
The second edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" challenges featured five data-impaired challenges, where models are trained from scra…
Domain Adaptation for Rare Classes Augmented with Synthetic Samples
Tuhin Das, Robert-Jan Bruintjes, Attila Lengyel +2
To alleviate lower classification performance on rare classes in imbalanced datasets, a possible solution is to augment the underrepresented classes with synthetic samples. Domain…
Zero-Shot Day-Night Domain Adaptation with a Physics Prior
Attila Lengyel, Sourav Garg, Michael Milford +1
We explore the zero-shot setting for day-night domain adaptation. The traditional domain adaptation setting is to train on one domain and adapt to the target domain by exploiting u…
Exploiting Learned Symmetries in Group Equivariant Convolutions
Attila Lengyel, Jan C. van Gemert
Group Equivariant Convolutions (GConvs) enable convolutional neural networks to be equivariant to various transformation groups, but at an additional parameter and compute cost. We…
VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
Robert-Jan Bruintjes, Attila Lengyel, Marcos Baptista Rios +2
We present the first edition of "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" challenges. We offer four data-impaired challenges, where models are trained fr…
Evaluating the performance of the LIME and Grad-CAM explanation methods on a LEGO multi-label image classification task
David Cian, Jan van Gemert, Attila Lengyel
In this paper, we run two methods of explanation, namely LIME and Grad-CAM, on a convolutional neural network trained to label images with the LEGO bricks that are visible in them.…