Genetic Algorithms for the Optimization of Diffusion Parameters in Content-Based Image Retrieval

Several computer vision and artificial intelligence projects are nowadays exploiting the manifold data distribution using, e.g., the diffusion process. This approach has produced dramatic improvements on the final performance thanks to the application of such algorithms to the kNN graph. Unfortunately, this recent technique needs a manual configuration of several parameters, thus it is not straightforward to find the best configuration for each dataset. Moreover, the brute-force approach is computationally very demanding when used to optimally set the parameters of the diffusion approach. We propose to use genetic algorithms to find the optimal setting of all the diffusion parameters with respect to retrieval performance for each different dataset. Our approach is faster than others used as references (brute-force, random-search and PSO). A comparison with these methods has been made on three public image datasets: Oxford5k, Paris6k and Oxford105k.

[1]  Thomas Bäck,et al.  An Overview of Evolutionary Algorithms for Parameter Optimization , 1993, Evolutionary Computation.

[2]  F. Glover,et al.  Handbook of Metaheuristics , 2019, International Series in Operations Research & Management Science.

[3]  Yannis Avrithis,et al.  Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Piotr Indyk,et al.  Approximate nearest neighbors: towards removing the curse of dimensionality , 1998, STOC '98.

[5]  Oscar Cordón,et al.  A survey on image segmentation using metaheuristic-based deformable models: state of the art and critical analysis , 2016, Appl. Soft Comput..

[6]  Albert Gordo,et al.  Deep Image Retrieval: Learning Global Representations for Image Search , 2016, ECCV.

[7]  Stefano Cagnoni,et al.  What Can We Learn from Multi-Objective Meta-Optimization of Evolutionary Algorithms in Continuous Domains? , 2019 .

[8]  Yoshua Bengio,et al.  Algorithms for Hyper-Parameter Optimization , 2011, NIPS.

[9]  Albert Gordo,et al.  End-to-End Learning of Deep Visual Representations for Image Retrieval , 2016, International Journal of Computer Vision.

[10]  Kai Li,et al.  Efficient k-nearest neighbor graph construction for generic similarity measures , 2011, WWW.

[11]  Bernhard Schölkopf,et al.  Ranking on Data Manifolds , 2003, NIPS.

[12]  Simon Osindero,et al.  Cross-Dimensional Weighting for Aggregated Deep Convolutional Features , 2015, ECCV Workshops.

[13]  Michael Isard,et al.  Object retrieval with large vocabularies and fast spatial matching , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Michael Isard,et al.  Lost in quantization: Improving particular object retrieval in large scale image databases , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  John J. Grefenstette,et al.  Optimization of Control Parameters for Genetic Algorithms , 1986, IEEE Transactions on Systems, Man, and Cybernetics.

[16]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[17]  Ángel Corberán,et al.  Scatter search , 2003 .

[18]  Eva Mohedano,et al.  An Efficient Approximate kNN Graph Method for Diffusion on Image Retrieval , 2019, ICIAP.

[19]  Mark J. Huiskes,et al.  The MIR flickr retrieval evaluation , 2008, MIR '08.

[20]  Walter J. Gutjahr,et al.  Convergence Analysis of Metaheuristics , 2010, Matheuristics.

[21]  Andries P. Engelbrecht,et al.  Computational Intelligence: An Introduction , 2002 .

[22]  G. I. Balandina,et al.  Comparative Research of Random Search Algorithms and Evolutionary Algorithms for the Optimal Control Problem of the Mobile Robot , 2019, Procedia Computer Science.

[23]  A. E. Eiben,et al.  Introduction to Evolutionary Computing , 2003, Natural Computing Series.

[24]  Mark Hoogendoorn,et al.  Parameter Control in Evolutionary Algorithms: Trends and Challenges , 2015, IEEE Transactions on Evolutionary Computation.

[25]  Rajeev Motwani,et al.  The PageRank Citation Ranking : Bringing Order to the Web , 1999, WWW 1999.

[26]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[27]  Aaron Klein,et al.  BOHB: Robust and Efficient Hyperparameter Optimization at Scale , 2018, ICML.

[28]  Marc Parizeau,et al.  DEAP: evolutionary algorithms made easy , 2012, J. Mach. Learn. Res..

[29]  Federico Magliani,et al.  An accurate retrieval through R-MAC+ descriptors for landmark recognition , 2018, ICDSC.

[30]  Jason H. Moore,et al.  Investigating the parameter space of evolutionary algorithms , 2017, BioData Mining.

[31]  Federico Magliani,et al.  Landmark Recognition: From Small-Scale to Large-Scale Retrieval , 2018, Recent Advances in Computer Vision.

[32]  R. Mises,et al.  Praktische Verfahren der Gleichungsauflösung . , 1929 .

[33]  Zbigniew Michalewicz,et al.  Parameter Control in Evolutionary Algorithms , 2007, Parameter Setting in Evolutionary Algorithms.

[34]  María Cristina Riff,et al.  Tuners review: How crucial are set-up values to find effective parameter values? , 2018, Eng. Appl. Artif. Intell..

[35]  Holger H. Hoos,et al.  Automated Algorithm Configuration and Parameter Tuning , 2012, Autonomous Search.

[36]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[37]  Shin'ichi Satoh,et al.  Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing , 2018, AAAI.

[38]  Tommi Kärkkäinen,et al.  On automatic algorithm configuration of vehicle routing problem solvers , 2019, Journal on Vehicle Routing Algorithms.

[39]  Victor S. Lempitsky,et al.  Aggregating Local Deep Features for Image Retrieval , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[40]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.