Fast and Incremental Method for Loop-Closure Detection Using Bags of Visual Words
- Adrien Angeli, David Filliat, S. Doncieux, Jean-Arcady Meyer
- Computer ScienceIEEE Transactions on robotics
- 1 October 2008
This work presents an online method that makes it possible to detect when an image comes from an already perceived scene using local shape and color information, and extends the bag-of-words method used in image classification to incremental conditions and relies on Bayesian filtering to estimate loop-closure probability.
3D Hand Gesture Recognition Using a Depth and Skeletal Dataset
- Quentin De Smedt, H. Wannous, J. Vandeborre, J. Guerry, B. L. Saux, David Filliat
- Computer Science, Psychology3DOR@Eurographics
- 23 April 2017
This track is to evaluate the performance of recent recognition approaches using a challenging hand gesture dataset containing 14 gestures, performed by 28 participants executing the same gesture with two different numbers of fingers.
Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges
- Timothée Lesort, Vincenzo Lomonaco, A. Stoian, D. Maltoni, David Filliat, Natalia Díaz Rodríguez
- Computer ScienceInformation Fusion
- 29 June 2019
A visual bag of words method for interactive qualitative localization and mapping
- David Filliat
- Computer ScienceProceedings IEEE International Conference on…
- 10 April 2007
This work presents a visual localization and map-learning system that relies on vision only and that is able to incrementally learn to recognize the different rooms of an apartment from any robot position.
Map-based navigation in mobile robots: I. A review of localization strategies
- David Filliat, Jean-Arcady Meyer
- Computer ScienceCognitive Systems Research
- 1 December 2003
Generative Models from the perspective of Continual Learning
- Timothée Lesort, Hugo Caselles-Dupré, M. G. Ortiz, A. Stoian, David Filliat
- Computer ScienceIEEE International Joint Conference on Neural…
- 21 December 2018
It is found that among all models, the original GAN performs best and among Continual Learning strategies, generative replay outperforms all other methods.
State Representation Learning for Control: An Overview
- Timothée Lesort, Natalia Díaz Rodríguez, Jean-François Goudou, David Filliat
- Computer ScienceNeural Networks
- 12 February 2018
Symmetry-Based Disentangled Representation Learning requires Interaction with Environments
- Hugo Caselles-Dupré, M. G. Ortiz, David Filliat
- Computer ScienceNeural Information Processing Systems
- 30 March 2019
It is argued that Symmetry-Based Disentangled Representation Learning cannot only be based on static observations: agents should interact with the environment to discover its symmetries.
Visual topological SLAM and global localization
- Adrien Angeli, S. Doncieux, Jean-Arcady Meyer, David Filliat
- Computer ScienceIEEE International Conference on Robotics and…
- 12 May 2009
This work proposes an extension of this work by integrating metrical information from robot odometry in the topological map, so as to obtain a globally consistent environment model.
Don't forget, there is more than forgetting: new metrics for Continual Learning
- Natalia Díaz Rodríguez, Vincenzo Lomonaco, David Filliat, D. Maltoni
- Computer ScienceArXiv
- 31 October 2018
This work proposes a more comprehensive set of implementation independent metrics accounting for several factors worth considering in the deployment of real AI systems that learn continually: accuracy or performance over time, backward and forward knowledge transfer, memory overhead as well as computational efficiency.