DepictQA (with vision abstractor to reduce vision token numbers) model weights trained on DQ495K, KonIQ, and SPAQ datasets.
See https://github.com/XPixelGroup/DepictQA for details.
- Downloads last month
- 12
DepictQA (with vision abstractor to reduce vision token numbers) model weights trained on DQ495K, KonIQ, and SPAQ datasets.
See https://github.com/XPixelGroup/DepictQA for details.