Priming Neural Networks
This work addresses object detection and segmentation for computer vision applications, but it is incremental as it adapts a known biological concept to neural networks.
The paper tackled the problem of improving object detection and segmentation in challenging conditions like severe noise by mimicking visual priming from human vision, resulting in a method that is complementary and sometimes more effective than post-processing, with notable gains in hard-to-detect cases.
Visual priming is known to affect the human visual system to allow detection of scene elements, even those that may have been near unnoticeable before, such as the presence of camouflaged animals. This process has been shown to be an effect of top-down signaling in the visual system triggered by the said cue. In this paper, we propose a mechanism to mimic the process of priming in the context of object detection and segmentation. We view priming as having a modulatory, cue dependent effect on layers of features within a network. Our results show how such a process can be complementary to, and at times more effective than simple post-processing applied to the output of the network, notably so in cases where the object is hard to detect such as in severe noise. Moreover, we find the effects of priming are sometimes stronger when early visual layers are affected. Overall, our experiments confirm that top-down signals can go a long way in improving object detection and segmentation.