Open-Vocabulary Camouflaged Object Segmentation

arXiv:2311.11241v2 Announce Type: replace
Abstract: Recently, the emergence of the large-scale vision-language model (VLM), such as CLIP, has opened the way towards open-world object perception. Many works have explored the utilization of pre-trained VLM for the challenging open-vocabulary dense prediction task that requires perceiving diverse objects with novel classes at inference time. Existing methods construct experiments based on the public datasets of related tasks, which are not tailored for open vocabulary and rarely involve imperceptible objects camouflaged in complex scenes …

abstract arxiv clip construct cs.cv diverse emergence inference language language model novel object objects open-world perception prediction scale segmentation the way type vision vlm world