Back to Search
Start Over
An easy-to-hard learning strategy for within-image co-saliency detection
- Source :
- Neurocomputing. 358:166-176
- Publication Year :
- 2019
- Publisher :
- Elsevier BV, 2019.
-
Abstract
- Within-image co-saliency detection is to detect/highlight the common saliency (similar-appearance salient objects) in a single image. Ideally, it can be solved by detecting each individual salient object first and then comparing them, which is possible for some images with simple representations. However, in practice, this way is not accurate and robust for some images with complex representations. In this paper, we propose an easy-to-hard learning strategy to solve this problem. By directly localizing and comparing salient objects in simple images, superpixel confidences as co-salient objects are inferred by an easy learning method, which provide promising but also noisy supervisions for complex images. Therefore, within-image co-saliency detection in complex images can be modeled as a hard learning problem with noisy labels. A multi-scale Multiple Instance Learning (MIL) model together with a new sampling method is proposed to solve this hard learning problem with noisy labels. Experimental results show that the proposed method achieves the best performance on a public benchmark dataset and two synthetic datasets.
- Subjects :
- 0209 industrial biotechnology
business.industry
Computer science
Cognitive Neuroscience
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Pattern recognition
02 engineering and technology
Salient objects
Computer Science Applications
Image (mathematics)
020901 industrial engineering & automation
Artificial Intelligence
Simple (abstract algebra)
Salience (neuroscience)
0202 electrical engineering, electronic engineering, information engineering
Benchmark (computing)
020201 artificial intelligence & image processing
Artificial intelligence
business
Subjects
Details
- ISSN :
- 09252312
- Volume :
- 358
- Database :
- OpenAIRE
- Journal :
- Neurocomputing
- Accession number :
- edsair.doi...........dad264b69eed98873c588f3221d7e9e8