Evaluation of Localized Semantics: Data, Methodology, and Experiments

We present a new data set encoding localized semantics for 1014 images and a methodology for using this kind of data for recognition evaluation. This methodology establishes protocols for mapping algorithm specific localization (e.g., segmentations) to our data, handling synonyms, scoring matches at different levels of specificity, dealing with vocabularies with sense ambiguity (the usual case), and handling ground truth regions with multiple labels. Given these protocols, we develop two evaluation approaches. The first measures the range of semantics that an algorithm can recognize, and the second measures the frequency that an algorithm recognizes semantics correctly. The data, the image labeling tool, and programs implementing our evaluation strategy are all available on-line (kobus.ca//research/data/IJCV). We apply this infrastructure to evaluate four algorithms which learn to label image regions from weakly labeled data. The algorithms tested include two variants of multiple insta...

• Type: Journal
• Year: 2008
• Where: IJCV
• Authors: Kobus Barnard, Quanfu Fan, Ranjini Swaminathan, Anthony Hoogs, Roderic Collins, Pascale Rondot, John P. Kaufhold
• Keywords: Algorithm Specific Localization, Algorithms, IJCV 2008, Images