Office-Home

The 'Office-Home' dataset is a benchmark used to evaluate cross-domain image retrieval methods by containing images from various domains such as artistic and real-world scenes.

Papers using Office-Home (3)

Open Set Domain Adaptation With Vision-language Models Via Gradient-aware Separation2025Empowering Source-Free Domain Adaptation via MLLM-Guided Reliability-Based Curriculum Learning2024 · 1 citesCaption-Matching: A Multimodal Approach for Cross-Domain Image Retrieval2024