MASON: A Model AgnoStic ObjectNess Framework
arXiv:1809.07499
Abstract
This paper proposes a simple, yet very effective method to localize dominant foreground objects in an image, to pixel-level precision. The proposed method 'MASON' (Model-AgnoStic ObjectNess) uses a deep convolutional network to generate category-independent and model-agnostic heat maps for any image. The network is not explicitly trained for the task, and hence, can be used off-the-shelf in tandem with any other network or task. We show that this framework scales to a wide variety of images, and illustrate the effectiveness of MASON in three varied application contexts.
arXiv commentAccepted at AutoNUE Workshop, 15th European Conference on Computer Vision (ECCV), September 2018, Munich, Germany
References in corpus (5)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection