Add benchmark models from the literature to be able to test fast against new methods

lhackel-tub / ConfigILM

A Library for configurable combination of pre-configured and possibly pre-trained Image and Language Models

https://lhackel-tub.github.io/ConfigILM/

MIT License

37 stars 5 forks source link

Add benchmark models from the literature to be able to test fast against new methods #59

Open lhackel-tub opened 1 year ago

lhackel-tub commented 1 year ago

If the library implements some benchmark models using the configurations, it would be easier for end users to fast test against the existing methods. In addition these benchmarks would show as examples how the library could be used.

Possible starting points could be:

[ ] Language Transformers for Remote Sensing Visual Question Answering
[x] LiT-4-RSVQA: Lightweight Transformer-based Visual Question Answering in Remote Sensing

lhackel-tub commented 1 year ago

The second benchmark code is not added yet