Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels Heeseong Shin 1 Chaehyun Kim

Oct-9-2025, 18:49:52 GMT–Neural Information Processing Systems

Large-scale vision-language models like CLIP have demonstrated impressive open-vocabulary capabilities for image-level tasks, excelling in recognizing what objects are present.

machine learning, natural language, semantic segmentation, (16 more...)

Neural Information Processing Systems

Oct-9-2025, 18:49:52 GMT

Conferences PDF

Country:
- Asia > Middle East
  - Israel (0.04)
- Europe > Poland (0.04)

Genre:
- Research Report > Experimental Study (0.93)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Neural Networks
      - Deep Learning (0.67)
    - Natural Language > Text Processing (0.93)
    - Representation & Reasoning (1.00)
    - Vision (1.00)
  - Sensing and Signal Processing > Image Processing (0.93)