Today I experimented with different bounded classifiers for open set recognition. A bounding classifier essentially is a type of model which can detect out-of-distribution (OOD) samples, i.e. when presented with an image of a class it has not been trained on. In the image below, a bounded classifier would identify images found in the less dense regions as unknowns rather than try to fit them to a previously-learned class.
I performed my experiment evaluating different bounding classifiers by testing a Resnet50's accuracy in detecting out-of-distribution samples (original dataset is CUB200) either from generated Gaussian noise or the Oxford Flowers dataset. Here are two sample images from those respective dataloaders:
The results I achieved were very similar to those shown in this table (the third row is the CUB200 dataset):
I performed my experiment evaluating different bounding classifiers by testing a Resnet50's accuracy in detecting out-of-distribution samples (original dataset is CUB200) either from generated Gaussian noise or the Oxford Flowers dataset. Here are two sample images from those respective dataloaders:
The results I achieved were very similar to those shown in this table (the third row is the CUB200 dataset):
Tomorrow I hope to finally begin to look into the intersection of incremental learning and open set recognition (having experiment with both aspects individually). Then, I will be able to formulate a better idea of the kinds of results I can expect to see for my project.
Comments
Post a Comment