2015/05/01 by Hongping Cai, Cai, Hongping, Qi Wu +5 · 31 citations
Computer Science · Mathematics · Psychology · #68745 #Adaptation (eye) #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Art #Artificial intelligence #Benchmark (surveying) #Cartography #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Deep learning #Depiction #Domain (mathematical analysis) #Domain Adaptation and Few-Shot Learning #Domain adaptation #FOS: Computer and information sciences #Geography #I.2.10 #Mathematics #Object (grammar) #Psychology #Variety (cybernetics) #Visual arts #acm:68745 #cs.CV #msc:68745
paper · pdf · doi:10.48550/arxiv.1505.00110
published in arXiv (Cornell University) (Cornell University) · 12 pages, 6 figures
arxiv created 2015/05/01 · openalex publication_date 2015/05/01 · arxiv updated 2015/05/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
The cross-depiction problem is that of recognising visual objects regardless of whether they are photographed, painted, drawn, etc. It is a potentially significant yet under-researched problem. Emulating the remarkable human ability to recognise objects in an astonishingly wide variety of depictive forms is likely to advance both the foundations and the applications of Computer Vision. In this paper we benchmark classification, domain adaptation, and deep learning methods; demonstrating that none perform consistently well in the cross-depiction problem. Given the current interest in deep learning, the fact such methods exhibit the same behaviour as all but one other method: they show a significant fall in performance over inhomogeneous databases compared to their peak performance, which is always over data comprising photographs only. Rather, we find the methods that have strong models of spatial relations between parts tend to be more robust and therefore conclude that such information is important in modelling object classes regardless of appearance details.