1 code implementation • 29 Mar 2023 • Vasco Lopes, Bruno Degardin, Luís A. Alexandre
We found that only a subset of the operation pool is required to generate architectures close to the upper-bound of the performance range.
no code implementations • 22 Jul 2022 • Vasco Lopes, Miguel Santos, Bruno Degardin, Luís A. Alexandre
GEA guides the evolution by exploring the search space by generating and evaluating several architectures in each generation at initialisation stage using a zero-proxy estimator, where only the highest-scoring architecture is trained and kept for the next generation.
Ranked #16 on Neural Architecture Search on NAS-Bench-201, CIFAR-100
1 code implementation • 10 Mar 2022 • Vasco Lopes, Luís A. Alexandre
In this paper, we propose LCMNAS, a method that pushes NAS to less constrained search spaces by performing macro-search without relying on pre-defined heuristics or bounded search spaces.
1 code implementation • 28 Oct 2021 • Vasco Lopes, Miguel Santos, Bruno Degardin, Luís A. Alexandre
The rationale behind G-EA, is to explore the search space by generating and evaluating several architectures in each generation at initialization stage using a zero-proxy estimator, where only the highest-scoring network is trained and kept for the next generation.
1 code implementation • 21 Oct 2021 • Bruno Degardin, João Neves, Vasco Lopes, João Brito, Ehsan Yaghoubi, Hugo Proença
Synthesising the spatial and temporal dynamics of the human body skeleton remains a challenging task, not only in terms of the quality of the generated shapes, but also of their diversity, particularly to synthesise realistic body movements of a specific action (action conditioning).
Ranked #1 on Human action generation on Human3.6M
no code implementations • 14 May 2021 • Bruno Degardin, Vasco Lopes, Hugo Proença
It is known that the kinematics of the human body skeleton reveals valuable information in action recognition.
no code implementations • 16 Feb 2021 • Vasco Lopes, António Gaspar, Luís A. Alexandre, João Cordeiro
Sentiment analysis is a research topic focused on analysing data to extract information related to the sentiment that it causes.
Ranked #1 on Multimodal Sentiment Analysis on B-T4SA
2 code implementations • 16 Feb 2021 • Vasco Lopes, Saeid Alirezazadeh, Luís A. Alexandre
In this paper, we propose EPE-NAS, an efficient performance estimation strategy, that mitigates the problem of evaluating networks, by scoring untrained networks and creating a correlation with their trained performance.
Ranked #26 on Neural Architecture Search on NAS-Bench-201, CIFAR-100
1 code implementation • 3 Sep 2020 • Vasco Lopes, Luís A. Alexandre
The dominant approach for surface defect detection is the use of hand-crafted feature-based methods.
Ranked #1 on Defect Detection on DAGM2007
no code implementations • 31 Jul 2020 • Vasco Lopes, Luís A. Alexandre
Neural Architecture Search has achieved state-of-the-art performance in a variety of tasks, out-performing human-designed networks.
no code implementations • 15 Apr 2020 • Vasco Lopes, Paulo Fazendeiro
Artificial Intelligence algorithms have been steadily increasing in popularity and usage.
2 code implementations • 13 Nov 2019 • João C. Neves, Ruben Tolosana, Ruben Vera-Rodriguez, Vasco Lopes, Hugo Proença, Julian Fierrez
The availability of large-scale facial databases, together with the remarkable progresses of deep learning technologies, in particular Generative Adversarial Networks (GANs), have led to the generation of extremely realistic fake facial content, raising obvious concerns about the potential for misuse.
no code implementations • 3 Sep 2019 • Vasco Lopes, Fabio Maria Carlucci, Pedro M Esperança, Marco Singh, Victor Gabillon, Antoine Yang, Hang Xu, Zewei Chen, Jun Wang
The Neural Architecture Search (NAS) problem is typically formulated as a graph search problem where the goal is to learn the optimal operations over edges in order to maximise a graph-level global objective.
no code implementations • 30 Sep 2018 • Vasco Lopes, Luís A. Alexandre
Blockchain technology is growing everyday at a fast-passed rhythm and it's possible to integrate it with many systems, namely Robotics with AI services.