Institution profile

Chiba University

Academic institutionasia · jp
Official website
Research library61linked papers
Opportunities0open roles
Selected work

Representative Papers

Explaining Object Detectors via Collective Contribution of Pixels

Dec 01, 2024arXiv.org

Existing interpretability methods for object detection predominantly rely on single-pixel attribution, failing to capture the joint influence of multi-pixel collaborations on both bounding box localization and class prediction—thus overlooking compositional cues or introducing spurious correlations. To address this, we introduce Shapley interaction values to object detection interpretation for the first time, proposing the first end-to-end differentiable framework that explicitly models high-order cooperative effects among pixel groups. Our approach jointly models feature-space perturbations and detection output sensitivity to simultaneously quantify individual pixel contributions and higher-order interactions. Extensive experiments on COCO and other benchmarks demonstrate that our method significantly outperforms state-of-the-art interpretability baselines. Both qualitative visualizations and quantitative metrics confirm its superior ability to localize discriminative visual regions accurately. The source code will be made publicly available.

2 citationsRead paper

Spatio-temporal smoothing, interpolation and prediction of income distributions based on grouped data

Jul 18, 2022

Japanese municipal-level household income data—derived from the Household Labour Survey (HLS)—suffer from severe limitations: coarse income grouping, incomplete spatial coverage, and low temporal frequency (only quinquennial). These constraints impede evidence-based local policymaking. To address this, we propose the Spatio-Temporal Finite Mixture Model (ST-FMM), the first framework to jointly capture regional heterogeneity and dynamic evolution via a “shared latent income distribution + spatio-temporally varying mixture proportions” mechanism. ST-FMM integrates grouped-data likelihood modeling, EM-based parameter estimation, and a Bayesian smoothing–prediction framework to impute missing municipalities, smooth distributional estimates, and forecast future time points. The model generates complete, high-resolution municipal-level maps of income distributions and poverty metrics. Empirical results demonstrate substantial improvements in spatial coverage, distributional fidelity, and temporal responsiveness—enabling faster, more precise, and geographically targeted policy interventions.

1 citationsRead paper

Bayesian spatiotemporal conditional autoregressive model for local temporal variations

Sep 05, 2026

Spatiotemporal areal data are commonly observed in various fields such including epidemiology, social science, economics and so on. To capture both spatial trends and temporal trends, spatiotemporal modeling is often employed, and the conditional autoregressive (CAR) model is one of the most widely used approaches for modeling areal data. This paper proposes a new framework for estimating spatiotemporal trends based on the CAR model. The proposed method provides locally adaptive temporal smoothing while yielding interpretable temporal trends by effectively utilizing information from both spatially neighboring areas and temporally adjacent time points. We also develop a Gibbs sampling algorithm and demonstrate the ability of the proposed method to adapt to to local temporal changes through numerical examples.

0 citationsRead paper
Recent publications

Latest Papers

Bayesian spatiotemporal conditional autoregressive model for local temporal variations

Sep 05, 2026

Spatiotemporal areal data are commonly observed in various fields such including epidemiology, social science, economics and so on. To capture both spatial trends and temporal trends, spatiotemporal modeling is often employed, and the conditional autoregressive (CAR) model is one of the most widely used approaches for modeling areal data. This paper proposes a new framework for estimating spatiotemporal trends based on the CAR model. The proposed method provides locally adaptive temporal smoothing while yielding interpretable temporal trends by effectively utilizing information from both spatially neighboring areas and temporally adjacent time points. We also develop a Gibbs sampling algorithm and demonstrate the ability of the proposed method to adapt to to local temporal changes through numerical examples.

0 citationsRead paper

Benchmarking and Reasoning Distillation of Large Language Models for Feedback Controller Design in Complex Dynamical Systems

Aug 07, 2026

This study addresses the lack of effective evaluation benchmarks and unclear edge-deployment capabilities of large language models (LLMs) in designing feedback controllers for complex dynamic systems. The authors introduce CoDyControlBench, the first multidimensional benchmark encompassing 132 system configurations across five dimensions—including degrees of freedom and system type—to systematically evaluate the control design capabilities of six prominent LLMs. They further propose a reasoning-distillation-based approach to derive lightweight models suitable for edge deployment. Experimental results show that GPT achieves a 94.8% success rate on this benchmark. The distilled 1.5B-parameter model demonstrates stable performance in simulations across systems with 1–6 degrees of freedom and attains 100% target-tracking success in real-world experiments on a pneumatic artificial muscle robotic arm, significantly enhancing both performance and generalization of edge-deployable controllers.

0 citationsRead paper