Appendix for Dictionary Enriched Visual Concept Paralleled training for Open world Detection A Negative Impacts and Limitations

YFCC [11], we expect to extend our method to larger image-text pair datasets from the Internet. Region Proposal Network (RPN) pre-trained on Objects365 to extract object proposals. To alleviate the partial-label problem, we use concept names from our proposed concept dictionary (Sec.3.2) instead of the raw caption as the text input. Following CLIP, the prompt "a photo of a category." The explanation of each dataset can be found in the table caption.