Detecting People in Cubist Art
This work addresses the problem of assessing whether computer vision algorithms can match human visual robustness in extreme conditions, such as abstract art, for researchers in AI and cognitive science, though it is incremental as it applies existing methods to new data.
The paper evaluated existing object detection methods on Cubist art, specifically Picasso paintings, to compare human vision with algorithms under extreme distortion. Results showed that human perception significantly outperforms current methods, but both exhibit similar graceful degradation as objects become more abstract and fragmented.
Although the human visual system is surprisingly robust to extreme distortion when recognizing objects, most evaluations of computer object detection methods focus only on robustness to natural form deformations such as people's pose changes. To determine whether algorithms truly mirror the flexibility of human vision, they must be compared against human vision at its limits. For example, in Cubist abstract art, painted objects are distorted by object fragmentation and part-reorganization, to the point that human vision often fails to recognize them. In this paper, we evaluate existing object detection methods on these abstract renditions of objects, comparing human annotators to four state-of-the-art object detectors on a corpus of Picasso paintings. Our results demonstrate that while human perception significantly outperforms current methods, human perception and part-based models exhibit a similarly graceful degradation in object detection performance as the objects become increasingly abstract and fragmented, corroborating the theory of part-based object representation in the brain.