Benchmarking Object Detectors with COCO: A New Path Forward

arXiv:2403.18819v1 Announce Type: new
Abstract: The Common Objects in Context (COCO) dataset has been instrumental in benchmarking object detectors over the past decade. Like every dataset, COCO contains subtle errors and imperfections stemming from its annotation procedure. With the advent of high-performing models, we ask whether these errors of COCO are hindering its utility in reliably benchmarking further progress. In search for an answer, we inspect thousands of masks from COCO (2017 version) and uncover different types of errors such …

arxiv benchmarking coco cs.cv object path type