Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection
Dalian University of Technology · Inception Institute of Artificial Intelligence · +1 more institution
Abstract
The recently proposed camouflaged object detection (COD) attempts to segment objects that are visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios. Apart from high intrinsic similarity between the camouflaged objects and their background, the objects are usually diverse in scale, fuzzy in appearance, and even severely occluded. To deal with these problems, we propose a mixed-scale triplet network, Zoom- Net, which mimics the behavior of humans when observing vague images, i.e., zooming in and out. Specifically, our ZoomNet employs the zoom strategy to learn the discriminative mixed-scale semantics by the designed scale integration unit and hierarchical…
Citation impact
- FWCI
- 22.78
- Percentile
- 100%
- References
- 79
Authors
5Topics & keywords
- Computer science
- Zoom
- Generality
- Artificial intelligence
- Discriminative model
- Scale (ratio)
- Task (project management)
- Object detection
- Reduced inequalities