Multi-level image classification

Hello All,

is it possible to do image classification in two stages similar to the problem discussed by @Rohitagarwal257 described here multi-level image classification.

Briefly, i’m trying to train a model in multi-stages where stage 1 model identifies an item to a category and base on the outcome

stage 2 proceeds to do a identification within each group seperated by stage 1 into sub-categories… i.e. the outcomes in stage one determines the outcome in stage 2.

My first thought would be two models that you run one after the other. The first for stage 1, the second for stage 2.

@muellerzr do you have any example or links to a page where this has been done before. The problem might look easy but its quite complicated.

Ah let me try to rethink what you are saying to make sure I understand. We’ll say that model 1’s initial classification has 3 categories, but then each of those 3 additional categories have their own separate classifications that are needed that are not related to the other classes?

Is that closer?

After reading the post, perhaps mabye multi-label classification like the planets dataset? (I did not see that offered as a suggestion)

1 Like

Thats exactly what i’m attempting… I’ve tried planet format but the result are meaningless for my application… it would be nice if there is a way to structure this as a multi-level classification problem