Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation
cs.CV, cs.AI
Submitted: 2026-03-24
Updated: 2026-03-24
Code: https://github.com/2btlFe/GLA-CLIP
Terminology
Sources
- Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation
- Vision Transformers Need Registers
- Open-Vocabulary Universal Image Segmentation with MaskCLIP
- DINOv2: Learning Robust Visual Features without Supervision
- Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation
- DINOv3
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs