I was reading the well know paper Fully Convolutional Networks for Semantic Segmentation and throughout the whole paper they talk use the term fine and coarse. I was wondering what the meant. The first time they say it in the intro is:
Convolutional networks are driving advances in recognition. Convnets are not only improving for whole-image classification [19, 31, 32], but also making progress on local tasks with structured output. These include advances in bounding box object detection [29, 12, 17], part and keypoint prediction [39, 24], and local correspondence [24, 9]. The natural next step in the progression from coarse to fine inference is to make a prediction at every pixel.
what does that mean in the context of this paper? But also more importantly general computer vision?
Fine vs Coarse in normal English:
I know that coarse in English means "rough or loose in texture or grain" but that wasn't super helpful for me to figure out what it meant...any ideas? help?
Fine: From google: "involving great attention to detail.", "(chiefly of wood) having a fine or delicate arrangement of fibers."
For examples of use of that word on the paper:
- The natural next step in the progression from coarse to fine inference is to make a prediction at every pixel.
- We next explain how to convert classification nets into fully convolutional nets that produce coarse output maps.