5,337
edits
Line 915: | Line 915: | ||
Context is a 1-2% idea. Traditionally, it has only provided 1-2% of improved performance. | Context is a 1-2% idea. Traditionally, it has only provided 1-2% of improved performance. | ||
When is context helpful? | ;When is context helpful? | ||
When | * Typical answer: to ''guess'' small/blurry objects based on a prior. | ||
* Deeper answer: to make sense of the visual world. | |||
** When to use context and when not to use context. | |||
** 80% of context is automatically handled by neural networks, but 20% of work still remains. | |||
;Why context is important? | |||
* To resolve ambiguity. | |||
** Even high-res objects can be ambiguous. | |||
** There are 30,000+ types of objects but only a few can occur in an image. | |||
* To notice ''unusual'' things. | |||
* In infer function of unknown object. | |||
===Pixel Context=== | |||
Look at nearby pixels by inputting a slightly bigger region. | |||
===Semantic Context=== | |||
Use other objects present to answer what is present in the target pixels. | |||
===Geometric Context=== | |||
[Hoiem ''et al.'' 2005] | |||
Use segmentation to interpret geometry: | |||
* Sky | |||
* Ground | |||
* Building with normal of direction | |||
===Photometric Context=== | |||
If you know where the camera is, you can estimate the size of people and cars. | |||
If you know where the sun is, you can estimate where the scene | |||
===Geographic Context=== | |||
===Autocontext=== | |||
Do a prediction and then feed in the output to the model again for the model to refine the prediction. | |||
This is similar to pose machines, hourglass networks, iterative bounding box regression. | |||
===Classemes=== | |||
Descriptor is formed by concatenating outputs of weakly trained classifiers. | |||
==Will be on the exam== | ==Will be on the exam== |