The Show or Tell benchmark compares text and visual prompts for semantic segmentation on 14 datasets, finding visual prompts yield higher average mIoU but with high variance and much higher computational cost.
What a mess: Multi-domain evaluation of zero-shot semantic segmentation.Advances in Neural Infor- mation Processing Systems, 36:73299–73311, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Show or Tell? A Benchmark To Evaluate Visual and Textual Prompts in Semantic Segmentation
The Show or Tell benchmark compares text and visual prompts for semantic segmentation on 14 datasets, finding visual prompts yield higher average mIoU but with high variance and much higher computational cost.