ESC-Net combines CLIP with pre-trained SAM decoder blocks fed by pseudo prompts from image-text correlations to reach state-of-the-art open-vocabulary segmentation on three major benchmarks.
Zero-shot semantic segmentation.Advances in Neural Information Processing Systems, 32, 2019
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Effective SAM Combination for Open-Vocabulary Semantic Segmentation
ESC-Net combines CLIP with pre-trained SAM decoder blocks fed by pseudo prompts from image-text correlations to reach state-of-the-art open-vocabulary segmentation on three major benchmarks.