GenSAM
A general text prompting method for camouflage object segmentation.
CommonProductImageImage ProcessingImage Generation
GenSAM is a method for camouflage object detection (COD) that utilizes Cross-modal Chains of Thought Prompting (CCTP) technology to understand visual prompts and leverages general text prompts to obtain reliable visual prompts. The method achieves efficient and accurate camouflage object segmentation through progressive masking generation (PMG) during testing, automatically generating and optimizing visual prompts without additional training.
GenSAM Visit Over Time
Monthly Visits
587
Bounce Rate
44.39%
Page per Visit
1.0
Visit Duration
00:00:00