Now that most participants have a good baseline ready , I think this is the time when we need to think about the actual task at hand i.e. Purchase phase. So far people have been using Random sampling which from my point of view should only act as a purchase baseline and not anything more than that.
Bird Eye View on the Problem
We are dealing with a standard Active Learning problem, more specifically it’s a Pool-based sampling problem. In such cases, the algorithm (DL model) attempts to evaluate the entire unlabelled dataset before it selects the best query (image) or set of queries (images).
I was doing some readings and I thought it will awesome to share those with the whole community. These methods have been greatly used over the years in such situations.
1. Deep Bayesian Active Learning with Image Data
2. Batch aware methods
3. Learning Loss for Active Learning
4. Mode collapse in active learning
Send some if this post was of any help