Visual Learning and Recognition
Notes for CMSC828I Visual Learning and Recognition (Fall 2020) taught by Abhinav Shrivastava
This class covers:
- How a sub-topic evolved
- State of the art
Introduction to Data
September 8
The extremes of data.
If we have very few images, we are working on an extrapolation problem.
As we approach an infinite number of training samples, learning becomes an interpolation problem.
Traditional datasets are in the order of \(10^2-10^4\) training samples.
Current datasets are in the order of \(10^5-10^7\) training samples.
In tiny images [1], Torrabla et al. use 80 million tiny images.
Data-driven Methods in Vision
Will be on the exam
- Back-prop and SGD,
- Softmax, sigmoid, cross entropy
Misc
References
- ↑ Antonio Torralba, Rob Fergus and William T. Freeman (2008). 80 million tiny images: a large dataset for non-parametric object and scene recognition (PAMI 2008) https://people.csail.mit.edu/torralba/publications/80millionImages.pdf