Automated Design of Salient Object Detection Algorithms with Brain Programming

• URL: http://arxiv.org/abs/2204.03722v1
• Date: Thu, 7 Apr 2022 20:21:30 GMT
• Title: Automated Design of Salient Object Detection Algorithms with Brain Programming
• Authors: Gustavo Olague, Jose Armando Menendez-Clavijo, Matthieu Olague, Arturo Ocampo, Gerardo Ibarra-Vazquez, Rocio Ochoa and Roberto Pineda
• Abstract summary: This research work proposes expanding the artificial dorsal stream using a recent proposal to solve salient object detection problems. We decided to apply the fusion of visual saliency and image segmentation algorithms as a template. We present results on a benchmark designed by experts with outstanding results in comparison with the state-of-the-art.
• Score: 3.518016233072556
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Despite recent improvements in computer vision, artificial visual systems' design is still daunting since an explanation of visual computing algorithms remains elusive. Salient object detection is one problem that is still open due to the difficulty of understanding the brain's inner workings. Progress on this research area follows the traditional path of hand-made designs using neuroscience knowledge. In recent years two different approaches based on genetic programming appear to enhance their technique. One follows the idea of combining previous hand-made methods through genetic programming and fuzzy logic. The other approach consists of improving the inner computational structures of basic hand-made models through artificial evolution. This research work proposes expanding the artificial dorsal stream using a recent proposal to solve salient object detection problems. This approach uses the benefits of the two main aspects of this research area: fixation prediction and detection of salient objects. We decided to apply the fusion of visual saliency and image segmentation algorithms as a template. The proposed methodology discovers several critical structures in the template through artificial evolution. We present results on a benchmark designed by experts with outstanding results in comparison with the state-of-the-art.

Related papers

• Automated Metaheuristic Algorithm Design with Autoregressive Learning [25.967262411437403]
  Current automated methods design algorithms within a fixed structure and operate from scratch. This paper proposes an autoregressive learning-based designer for automated design of metaheuristic algorithms.
  arXiv  Detail & Related papers  (2024-05-06T12:36:17Z)
• Automatic Discovery of Visual Circuits [66.99553804855931]
  We explore scalable methods for extracting the subgraph of a vision model's computational graph that underlies recognition of a specific visual concept. We find that our approach extracts circuits that causally affect model output, and that editing these circuits can defend large pretrained models from adversarial attacks.
  arXiv  Detail & Related papers  (2024-04-22T17:00:57Z)
• Artificial Bee Colony optimization of Deep Convolutional Neural Networks in the context of Biomedical Imaging [9.334663477968027]
  We propose a novel, hybrid neuroevolutive algorithm that integrates the Artificial Bee Colony Algorithm with Evolutionary Computation tools to generate models from scratch. The Chimera Algorithm has been validated with two datasets of natural and medical images, producing models that surpassed the performance of those coming from Transfer Learning.
  arXiv  Detail & Related papers  (2024-02-23T10:21:03Z)
• A Neuro-mimetic Realization of the Common Model of Cognition via Hebbian Learning and Free Energy Minimization [55.11642177631929]
  Large neural generative models are capable of synthesizing semantically rich passages of text or producing complex images. We discuss the COGnitive Neural GENerative system, such an architecture that casts the Common Model of Cognition.
  arXiv  Detail & Related papers  (2023-10-14T23:28:48Z)
• Analysis of Explainable Artificial Intelligence Methods on Medical Image Classification [0.0]
  The use of deep learning in computer vision tasks such as image classification has led to a rapid increase in the performance of such systems. Medical image classification systems are being adopted due to their high accuracy and near parity with human physicians in many tasks. The research techniques being used to gain insight into the black-box models are in the field of explainable artificial intelligence (XAI)
  arXiv  Detail & Related papers  (2022-12-10T06:17:43Z)
• Ultrasound Signal Processing: From Models to Deep Learning [64.56774869055826]
  Medical ultrasound imaging relies heavily on high-quality signal processing to provide reliable and interpretable image reconstructions. Deep learning based methods, which are optimized in a data-driven fashion, have gained popularity. A relatively new paradigm combines the power of the two: leveraging data-driven deep learning, as well as exploiting domain knowledge.
  arXiv  Detail & Related papers  (2022-04-09T13:04:36Z)
• Deep Algorithm Unrolling for Biomedical Imaging [99.73317152134028]
  In this chapter, we review biomedical applications and breakthroughs via leveraging algorithm unrolling. We trace the origin of algorithm unrolling and provide a comprehensive tutorial on how to unroll iterative algorithms into deep networks. We conclude the chapter by discussing open challenges, and suggesting future research directions.
  arXiv  Detail & Related papers  (2021-08-15T01:06:26Z)
• On the Exploitation of Neuroevolutionary Information: Analyzing the Past for a More Efficient Future [60.99717891994599]
  We propose an approach that extracts information from neuroevolutionary runs, and use it to build a metamodel. We inspect the best structures found during neuroevolutionary searches of generative adversarial networks with varying characteristics.
  arXiv  Detail & Related papers  (2021-05-26T20:55:29Z)
• Qualities, challenges and future of genetic algorithms: a literature review [0.0]
  Genetic algorithms are computer programs that simulate natural evolution. They have been used to solve various optimisation problems from neural network architecture search to strategic games. Recent developments such as GPU, parallel and quantum computing, conception of powerful parameter control methods, and novel approaches in representation strategies may be keys to overcome their limitations.
  arXiv  Detail & Related papers  (2020-11-05T17:53:33Z)
• A Deep Genetic Programming based Methodology for Art Media Classification Robust to Adversarial Perturbations [1.6148039130053087]
  Art Media Classification problem is a current research area that has attracted attention due to the complex extraction and analysis of features of high-value art pieces. A major concern related to its reliability has brought attention because, with small perturbations made intentionally in the input image (adversarial attack), its prediction can be completely changed. This work presents a Deep Genetic Programming method, called Brain Programming, that competes with deep learning.
  arXiv  Detail & Related papers  (2020-10-03T00:36:34Z)
• AutoML-Zero: Evolving Machine Learning Algorithms From Scratch [76.83052807776276]
  We show that it is possible to automatically discover complete machine learning algorithms just using basic mathematical operations as building blocks. We demonstrate this by introducing a novel framework that significantly reduces human bias through a generic search space. We believe these preliminary successes in discovering machine learning algorithms from scratch indicate a promising new direction in the field.
  arXiv  Detail & Related papers  (2020-03-06T19:00:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.