Environment exploration for object-based visual saliency learning

Craye, Céline; Filliat, David; Goudou, Jean-François

doi:10.1109/icra.2016.7487379

Cited by 69 publications

(53 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Benefiting from the capability of detecting the most visually distinctive objects from a given image, salient object detection plays an important role in many computer vision tasks, such as visual tracking [8], content-aware image editing [4], and robot navigation [5]. Traditional methods [11,25,14,31,2,12,41,3] mostly rely on hand-crafted features to capture local details and global context separately or simultaneously, but the lack of high-level semantic information restricts their ability to detect the integral salient objects in complex scenes.…”

Section: Introductionmentioning

confidence: 99%

A Simple Pooling-Based Design for Real-Time Salient Object Detection

Liu

Hou

Cheng

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

923

627

View full text Add to dashboard Cite

We solve the problem of salient object detection by investigating how to expand the role of pooling in convolutional neural networks. Based on the U-shape architecture, we first build a global guidance module (GGM) upon the bottom-up pathway, aiming at providing layers at different feature levels the location information of potential salient objects. We further design a feature aggregation module (FAM) to make the coarse-level semantic information well fused with the fine-level features from the top-down pathway. By adding FAMs after the fusion operations in the topdown pathway, coarse-level features from the GGM can be seamlessly merged with features at various scales. These two pooling-based modules allow the high-level semantic features to be progressively refined, yielding detail enriched saliency maps. Experiment results show that our proposed approach can more accurately locate the salient objects with sharpened details and hence substantially improve the performance compared to the previous state-of-the-arts. Our approach is fast as well and can run at a speed of more than 30 FPS when processing a 300 × 400 image. Code can be found at http://mmcheng.net/poolnet/.

show abstract

Section: Introductionmentioning

confidence: 99%

A Simple Pooling-Based Design for Real-Time Salient Object Detection

Liu

Hou

Cheng

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

923

627

View full text Add to dashboard Cite

show abstract

“…In a previous work [9], we described the core mechanism of the online learning of saliency based on depth segmentation and demonstrated its efficiency compared to state-of-the-art techniques. We here propose a way to use the generated saliency maps to produce boxes proposals for objects in the environment.…”

Section: Introductionmentioning

confidence: 99%

“…We here propose a way to use the generated saliency maps to produce boxes proposals for objects in the environment. Second, we presented in [9] some preliminary results of our exploration mechanism based on the Intelligent Adaptive Curiosity (IAC) [17], adapted to the problem of saliency learning. At that time, we successfully applied IAC in a semi-simulated setup so that an accurate saliency model could be learned with a limited number of relevant visual samples.…”

Section: Introductionmentioning

confidence: 99%

RL-IAC: An exploration policy for online saliency learning on an autonomous mobile robot

Craye

Filliat

Goudou

2016

2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

In the context of visual object search and localization, saliency maps provide an efficient way to find object candidates in images. Unlike most approaches, we propose a way to learn saliency maps directly on a robot, by exploring the environment, discovering salient objects using geometric cues, and learning their visual aspects. More importantly, we provide an autonomous exploration strategy able to drive the robot for the task of learning saliency. For that, we describe the Reinforcement Learning-Intelligent Adaptive Curiosity algorithm (RL-IAC), a mechanism based on IAC (Intelligent Adaptive Curiosity) able to guide the robot through areas of the space where learning progress is high, while minimizing the time spent to move in its environment without learning. We demonstrate first that our saliency approach is an efficient tool to generate relevant object boxes proposal in the input image and significantly outperforms the state-of-the-art EdgeBoxes algorithm. Second, we show that RL-IAC can drastically decrease the required time for learning saliency compared to random exploration.

show abstract

“…We instead use an object detector based on the depth-map to this end. This depth-based object detection has been described in previous publications that one could refer to for more details [14], [15]. Apart from this, the saliency learning process is exactly the same.…”

Section: A Experimental Setupmentioning

confidence: 98%

BioVision: A Biomimetics Platform for Intrinsically Motivated Visual Saliency Learning

2019

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

Abstract-We present BioVision, a bio-mimetics platform based on the human visual system. BioVision relies on the foveal vision principle based on a set of cameras with wide and narrow fields of view. We present in this platform a mechanism for learning visual saliency in an intrinsically motivated fashion. This model of saliency, learned and improved on-the-fly during the robot's exploration provides an efficient tool for localizing relevant objects within their environment.The proposed approach includes two intertwined components. On the one hand, a method for learning and incrementally updating a model of visual saliency from foveal observations. On the other hand, we investigate an autonomous exploration technique to efficiently learn such a saliency model. The proposed exploration, based on the IAC (Intelligent Adaptive Curiosity) algorithm is able to drive the robot's exploration so that samples selected by the robot are likely to improve the current model of saliency.We then demonstrate that such a saliency model learned directly on a robot outperforms several state-of-the-art saliency techniques, and that IAC can drastically decrease the required time for learning a reliable saliency model. We also investigate the behavior of IAC in a non static environment, and how well this algorithm can adapt to changes.

show abstract

Environment exploration for object-based visual saliency learning

Cited by 69 publications

References 20 publications

A Simple Pooling-Based Design for Real-Time Salient Object Detection

A Simple Pooling-Based Design for Real-Time Salient Object Detection

RL-IAC: An exploration policy for online saliency learning on an autonomous mobile robot

BioVision: A Biomimetics Platform for Intrinsically Motivated Visual Saliency Learning

Contact Info

Product

Resources

About