Soma Nonaka

Soma Nonaka

Auto-generated profile, based on publicly available information

Soma Nonaka

Graduate School of Informatics, Kyoto University, Kyoto, Japan

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 August 2021 in iScience
Verified
Journal Article
Open access
SNSoma Nonaka
Soma Nonaka
KMKei Majima
Kei Majima
SAShuntaro C. Aoki
Shuntaro C. Aoki
YKYukiyasu Kamitani
Yukiyasu Kamitani
Achievement of human-level image recognition by deep neural networks (DNNs) has spurred interest in whether and how DNNs are brain-like. Both DNNs and the visual cortex perform hierarchical processing, and correspondence has been shown between hierarchical visual areas and DNN layers in representing visual features. Here, we propose the brain hierarchy (BH) score as a metric to quantify the degree of hierarchical correspondence based on neural decoding and encoding analyses where DNN unit activations and human brain activity are predicted from each other. We find that BH scores for 29 pre-trained DNNs with various architectures are negatively correlated with image recognition performance, thus indicating that recently developed high-performance DNNs are not necessarily brain-like. Experimental manipulations of DNN models suggest that single-path sequential feedforward architecture with broad spatial integration is critical to brain-like hierarchy. Our method may provide new ways to design DNNs in light of their representational homology to the brain.

20 July 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
SLSang-Eun Lee
Sang-Eun Lee
KSKeisuke Shibata
Keisuke Shibata
SNSoma Nonaka
Soma Nonaka
SNShohei Nobuhara
Shohei Nobuhara
KNKo Nishino
Ko Nishino
We propose a novel camera calibration method for a room-scale multi-view imaging system. Our key idea is to leverage our articulated body movements as a calibration target. We show that a freely moving person provides trajectories of a set of oriented points ( e.g ., neck joint with spine direction) from which we can estimate the locations and poses of all cameras observing them. The method only requires the cameras to be synced and that 2D human poses are estimated in each view sequence. By elevating these 2D poses to 3D which directly provides a set of oriented 3D joints, we compute the extrinsic parameters of all cameras with a linear algorithm. We also show that this enables self-supervision of the 3D joint estimator for refinement, and the iteration of the two leads to accurate camera extrinsics and 3D pose estimates up to scale. Extensive experiments using synthetic and real data demonstrate the effectiveness and flexibility of the method. The method will serve as a useful tool to expand the utility of multi-view vision systems as it eliminates the need for cumbersome on-site calibration procedures.

24 July 2020 in bioRxiv
Verified
Preprint
Open access
PDF file
SNSoma Nonaka
Soma Nonaka
KMKei Majima
Kei Majima
SAShuntaro C. Aoki
Shuntaro C. Aoki
YKYukiyasu Kamitani
Yukiyasu Kamitani
Summary: Achievement of human-level image recognition by deep neural networks (DNNs) has spurred interest in whether and how DNNs are brain-like. Both DNNs and the visual cortex perform hierarchical processing, and correspondence has been shown between hierarchical visual areas and DNN layers in representing visual features. Here, we propose the brain hierarchy (BH) score as a metric to quantify the degree of hierarchical correspondence based on the decoding of individual DNN unit activations from human brain activity. We find that BH scores for 29 pretrained DNNs with varying architectures are negatively correlated with image recognition performance, indicating that recently developed high-performance DNNs are not necessarily brain-like. Experimental manipulations of DNN models suggest that relatively simple feedforward architecture with broad spatial integration is critical to brain-like hierarchy. Our method provides new ways for designing DNNs and understanding the brain in consideration of their representational homology.

1 January 2020 in SSRN Electronic Journal
Verified
Preprint
Open access
PDF file
SNSoma Nonaka
Soma Nonaka
KMKei Majima
Kei Majima
SAShuntaro C. Aoki
Shuntaro C. Aoki
YKYukiyasu Kamitani
Yukiyasu Kamitani
Achievement of human-level image recognition by deep neural networks (DNNs) has spurred interest in whether and how DNNs are brain-like. Both DNNs and the visual cortex perform hierarchical processing, and correspondence has been shown between hierarchical visual areas and DNN layers in representing visual features. Here, we propose the brain hierarchy (BH) score as a metric to quantify the degree of hierarchical correspondence based on the decoding of individual DNN unit activations from human brain activity. We find that BH scores for 29 pre-trained DNNs with varying architectures are negatively correlated with image recognition performance, indicating that recently developed high-performance DNNs are not necessarily brain-like. Experimental manipulations of DNN models suggest that relatively simple feedforward architecture with broad spatial integration is critical to brain-like hierarchy. Our method provides new ways for designing DNNs and understanding the brain in consideration of their representational homology.