PixFM25
* *Pixel-level understanding with Vision Foundation Models
* Hierarchical Semantic Segmentation with Autoregressive Language Modeling
* ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements
* Prompt-Guided Attention Head Selection for Focus-Oriented Image Retrieval
* Show or Tell? A Benchmark to Evaluate Visual and Textual Prompts in Semantic Segmentation