Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation

Benchmark Model Rank Results
camouflaged-object-segmentation-with-a-single-task-generic-prompt-on-camoProMaC#1E_{\phi}: 0.846F_{\beta}: 0.725MAE: 0.09S_{\alpha}: 0.767
camouflaged-object-segmentation-with-a-single-task-generic-prompt-on-cod10kProMaC#1E_{\phi}: 0.876F_{\beta}: 0.716MAE: 0.042S_{\alpha}: 0.805