Skip to Main content Skip to Navigation
Conference papers

Exploration Strategies for Incremental Learning of Object-Based Visual Saliency

Céline Craye 1, 2, 3 David Filliat 2, 1 Jean-François Goudou 3
2 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : Searching for objects in an indoor environment can be drastically improved if a task-specific visual saliency is available. We describe a method to learn such an object-based visual saliency in an intrinsically motivated way using an environment exploration mechanism. We first define saliency in a geometrical manner and use this definition to discover salient elements given an attentive but costly observation of the environment. These elements are used to train a fast classifier that predicts salient objects given large-scale visual features. In order to get a better and faster learning, we use intrinsic motivation to drive our observation selection, based on uncertainty and novelty detection. Our approach has been tested on RGB-D images, is real-time, and outperforms several state-of-the-art methods in the case of indoor object detection.
Document type :
Conference papers
Complete list of metadata

Cited literature [23 references]  Display  Hide  Download
Contributor : David Filliat <>
Submitted on : Wednesday, July 1, 2015 - 4:35:10 PM
Last modification on : Thursday, January 21, 2021 - 9:26:01 AM
Long-term archiving on: : Tuesday, April 25, 2017 - 10:00:20 PM


Files produced by the author(s)


  • HAL Id : hal-01170532, version 1



Céline Craye, David Filliat, Jean-François Goudou. Exploration Strategies for Incremental Learning of Object-Based Visual Saliency. Joint IEEE International Conference Developmental Learning and Epigenetic Robotics (ICDL-EPIROB), Aug 2015, Providence, United States. ⟨hal-01170532⟩



Record views


Files downloads