The research by Ben Lonnqvist, Zhengqing Wu, and Michael H. Herzog focuses on the role of neural noise in perceptual grouping and segmentation in deep neural networks (DNNs). They argue that neural noise can be used to separate objects from each other, and that adding noise in a DNN enables the network to segment images even without training on segmentation labels. They introduce the Good Gestalt datasets to test perceptual grouping, demonstrating that their DNN models reproduce important phenomena in human perception. Their findings suggest a novel unsupervised segmentation method requiring few assumptions, a new explanation for the formation of perceptual grouping, and a potential benefit of neural noise in the visual system.
Publication date: 28 Sep 2023
Project Page: https://arxiv.org/abs/2309.16515v1
Paper: https://arxiv.org/pdf/2309.16515
