ADE20K

The ADE20K dataset is a comprehensive benchmark that contains annotated images for semantic segmentation, used to evaluate the performance of models in understanding and interpreting complex scenes with various objects and backgrounds.

Papers using ADE20K (5)

SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning2026LangHOPS: Language Grounded Hierarchical Open-Vocabulary Part Segmentation2025Scene-aware Urban Design: A Human-ai Recommendation Framework Using Co-occurrence Embeddings And Vision-language Models2025Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models2023MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment2024