1 code implementation • 29 Nov 2023 • Thomas Dooms, Ing Jyh Tsang, Jose Oramas
Local learning, which focuses on updating subsets of a model's parameters at a time, has emerged as a promising technique to address these issues.
no code implementations • 22 Feb 2023 • Benjamin Vandersmissen, Jose Oramas
The Lottery Ticket Hypothesis (LTH) showed that by iteratively training a model, removing connections with the lowest global weight magnitude and rewinding the remaining connections, sparse networks can be extracted.
1 code implementation • 14 Feb 2023 • Benjamin Vandersmissen, Jose Oramas
We complement our study with sanity checks on the studied evaluation methods as a means to investigate their reliability and the impact of characteristics of the explanations on the evaluation methods.
no code implementations • International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications 2022 • Akash Singh, Tom De Schepper, Kevin Mets, Peter Hellinckx, Jose Oramas, Steven Latre
The proposed method achieves an improvement of around 1. 49% mAP in atomic action recognition and 17. 57% mAP in composite action recognition, over a I3D-NL baseline, on the CATER dataset.
Ranked #1 on Atomic action recognition on CATER (using extra training data)
no code implementations • 29 Sep 2021 • Kaili Wang, Jose Oramas, Tinne Tuytelaars
Explainable AI (XAI) methods focus on explaining what a neural network has learned - in other words, identifying the features that are the most influential to the prediction.
no code implementations • 29 Apr 2021 • Kaili Wang, Jose Oramas, Tinne Tuytelaars
One of the most common problems of weakly supervised object localization is that of inaccurate object coverage.
no code implementations • 16 Apr 2021 • Kaili Wang, Jose Oramas, Tinne Tuytelaars
Explainable AI (XAI) methods focus on explaining what a neural network has learned - in other words, identifying the features that are the most influential to the prediction.
no code implementations • 1 Jan 2021 • Akash Singh, Kevin Mets, Jose Oramas, Steven Latré
In this paper, we conduct a systematic analysis to explore the potential of CapsNets-based agents in the deep reinforcement learning setting.
no code implementations • 29 Oct 2020 • Roger Granda, Tinne Tuytelaars, Jose Oramas
We present a method for adversarial attack detection based on the inspection of a sparse set of neurons.
no code implementations • 16 Sep 2020 • Kaili Wang, Jose Oramas, Tinne Tuytelaars
Given a really low-resolution input image of a face (say 16x16 or 8x8 pixels), the goal of this paper is to reconstruct a high-resolution version thereof.
no code implementations • 23 Jan 2020 • Zehao Wang, Kaili Wang, Tinne Tuytelaars, Jose Oramas
In recent years, unsupervised/weakly-supervised conditional generative adversarial networks (GANs) have achieved many successes on the task of modeling and generating data.
no code implementations • 11 Sep 2019 • Kaili Wang, Jose Oramas, Tinne Tuytelaars
LSTMs have a proven track record in analyzing sequential data.
no code implementations • 5 Dec 2018 • Kaili Wang, Liqian Ma, Jose Oramas, Luc van Gool, Tinne Tuytelaars
We address the problem of unpaired geometric image-to-image translation.
no code implementations • ICLR 2019 • Jose Oramas, Kaili Wang, Tinne Tuytelaars
In this paper, we propose a novel scheme for both interpretation as well as explanation in which, given a pretrained model, we automatically identify internal features relevant for the set of classes considered by the model, without relying on additional annotations.
2 code implementations • 10 Jul 2017 • Kaili Wang, Yu-Hui Huang, Jose Oramas, Luc van Gool, Tinne Tuytelaars
Experiments on the Fashion 144k and a Pinterest-based dataset show that the automatic methods succeed at this task to a reasonable extent.
no code implementations • 21 Apr 2017 • Jose Oramas, Luc De Raedt, Tinne Tuytelaars
To estimate the viewpoint (or pose) of an object, people have mostly looked at object intrinsic features, such as shape or appearance.
no code implementations • 21 Jul 2016 • Marc Martínez-Camarena, Jose Oramas, Mario Montagud-Climent, Tinne Tuytelaars
Over the years, hand gesture recognition has been mostly addressed considering hand trajectories in isolation.
no code implementations • 31 Mar 2016 • Jose Oramas, Tinne Tuytelaars
At the base-level, our method identifies patterns of CNN activations with the aim of modeling different variations/styles in which objects of the classes of interest may occur.
1 code implementation • 6 Dec 2015 • Basura Fernando, Efstratios Gavves, Jose Oramas, Amir Ghodrati, Tinne Tuytelaars
We show how the parameters of a function that has been fit to the video data can serve as a robust new video representation.