[
    {
        "id": "osp-24630",
        "type": "article-journal",
        "title": "Natural Image Autoencoder-Based fMRI Representations for Trait and State Prediction",
        "author": [
            {
                "family": "Park",
                "given": "Juhyeon"
            },
            {
                "family": "Kim",
                "given": "Yeonwoo"
            },
            {
                "family": "Kim",
                "given": "Peter Yongho"
            },
            {
                "family": "Wang",
                "given": "Yansen"
            },
            {
                "family": "Xiao",
                "given": "Mingqing"
            },
            {
                "family": "Han",
                "given": "Dongqi"
            },
            {
                "family": "Li",
                "given": "Dongsheng"
            },
            {
                "family": "Moon",
                "given": "Taesup"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/natural-image-autoencoder-based-fmri-representations-for-trait-and-state-prediction",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Foundation models pre-trained on large-scale fMRI datasets have shown strong downstream performance, but at substantial data and computation cost. To investigate how much fMRI-specific pre-training is actually needed for such performance, we introduce FReD, which derives fMRI representations from a frozen Deep Compression AutoEncoder (DCAE) pre-trained exclusively on natural images and pairs them with a task specific readout. For trait prediction, FReD summarizes frame-wise representations by their temporal mean and log-standard deviation and applies linear probing, with late fusion across two normalization schemes. For state prediction, it represents each frame as a single token and models temporal dependencies with a shallow Transformer. Across four resting-state datasets spanning six trait-prediction targets, linear probes on frozen DCAE features generally outperform those on fMRI foundation model representations and remain competitive with fully fine-tuned fMRI foundation models. On three task-fMRI state-prediction tasks, a temporal readout on DCAE features performs comparably to the strongest foundation models evaluated. A Gaussian injection analysis further shows that localized signal changes are recovered more accurately from the frozen DCAE features than from the evaluated foundation-model representations. Together, these results show that strong performance on current fMRI benchmarks is possible without fMRI-specific representation pre-training, making frozen natural-image features as a useful baseline for assessing its added value."
    }
]