Category systems for real-world scenes
Matt D Anderson, Erich W Graf, James H Elder, Krista A Ehinger, Wendy J Adams
JOURNAL OF VISION | ASSOC RESEARCH VISION OPHTHALMOLOGY INC | Published : 2021
Categorization performance is a popular metric of scene recognition and understanding in behavioral and computational research. However, categorical constructs and their labels can be somewhat arbitrary. Derived from exhaustive vocabularies of place names (e.g., Deng et al., 2009), or the judgements of small groups of researchers (e.g., Fei-Fei, Iyer, Koch, & Perona, 2007), these categories may not correspond with human-preferred taxonomies. Here, we propose clustering by increasing the rand index via coordinate ascent (CIRCA): an unsupervised, data-driven clustering method for deriving ground-truth scene categories. In Experiment 1, human participants organized 80 stereoscopic images of out..View full abstract
Awarded by EPSRC
Supported by EPSRC grant EP/K005952/1, EPSRC grant EP/S016368/1, and a York University VISTA Visiting Trainee Award.