no code implementations • 22 Feb 2024 • Dmitry Kangin, Plamen Angelov
Through quantitative analysis, as well as qualitative interpretations of decision making, we demonstrate that the suggested method can improve upon existing baselines, as well as showcase the limitations of such approach yet to be solved.
no code implementations • 19 Nov 2023 • Plamen Angelov, Dmitry Kangin, Ziyang Zhang
The proposed framework named IDEAL (Interpretable-by-design DEep learning ALgorithms) recasts the standard supervised classification problem into a function of similarity to a set of prototypes derived from the training data, while taking advantage of existing latent spaces of large neural networks forming so-called Foundation Models (FM).
no code implementations • 23 Oct 2022 • Ziyang Zhang, Plamen Angelov, Eduardo Soares, Nicolas Longepe, Pierre Philippe Mathieu
Earth observation is fundamental for a range of human activities including flood response as it offers vital information to decision makers.
1 code implementation • CVPR 2022 • Zheheng Jiang, Hossein Rahmani, Plamen Angelov, Sue Black, Bryan M. Williams
Deep learning for graph matching has received growing interest and developed rapidly in the past decade.
Ranked #4 on Graph Matching on PASCAL VOC (matching accuracy metric)
1 code implementation • 4 Aug 2021 • Nathanael L. Baisa, Bryan Williams, Hossein Rahmani, Plamen Angelov, Sue Black
In this paper, we propose a novel hand-based person recognition method for the purpose of criminal investigations since the hand image is often the only available information in cases of serious crime such as sexual abuse.
no code implementations • 13 Jan 2021 • Nathanael L. Baisa, Bryan Williams, Hossein Rahmani, Plamen Angelov, Sue Black
Our proposed method, Global and Part-Aware Network (GPA-Net), creates global and local branches on the conv-layer for learning robust discriminative global and part-level features.
no code implementations • 16 Oct 2020 • Chia-Yen Chiang, Chloe Barnes, Plamen Angelov, Richard Jiang
Following the automated detection, we are able to automatically produce and calculate number of dead tree masks to label the dead trees in an image, as an indicator of forest health that could be linked to the causal analysis of environmental changes and the predictive likelihood of forest fire.
no code implementations • 2 Feb 2020 • Plamen Angelov, Eduardo Soares
In summary, we propose a new approach specifically advantageous for imbalanced multi-class problems that achieved two world records on well known hard benchmark problems and the best result on another problem in terms of accuracy.
no code implementations • 17 Dec 2019 • Xiaowei Gu, Muhammad Aurangzeb Khan, Plamen Angelov, Bikash Tiwary, Elnaz Shafipour Yourdshah, Zhao-Xu Yang
A novel self-organizing fuzzy proportional-integral-derivative (SOF-PID) control system is proposed in this paper.
no code implementations • 5 Dec 2019 • Plamen Angelov, Eduardo Soares
In this paper, we propose an elegant solution that is directly addressing the bottlenecks of the traditional deep learning approaches and offers a clearly explainable internal architecture that can outperform the existing methods, requires very little computational resources (no need for GPUs) and short training times (in the order of seconds).
no code implementations • 1 Nov 2019 • Eduardo Soares, Plamen Angelov
In this paper we offer a method and algorithm, which make possible fully autonomous (unsupervised) detection of new classes, and learning following a very parsimonious training priming (few labeled data samples only).
no code implementations • 18 Sep 2019 • Eduardo Soares, Plamen Angelov
Recidivism prediction provides decision makers with an assessment of the likelihood that a criminal defendant will reoffend that can be used in pre-trial decision-making.