الملخص
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.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Park, J., Kim, Y., Kim, P. Y., Wang, Y., Xiao, M., Han, D., Li, D., & Moon, T. (2026). Natural Image Autoencoder-Based fMRI Representations for Trait and State Prediction. https://omanscience.com/ar/articles/natural-image-autoencoder-based-fmri-representations-for-trait-and-state-prediction
MLA 9
Park, Juhyeon, et al. "Natural Image Autoencoder-Based fMRI Representations for Trait and State Prediction." https://omanscience.com/ar/articles/natural-image-autoencoder-based-fmri-representations-for-trait-and-state-prediction.
شيكاغو (المؤلف–التاريخ)
Park, Juhyeon, Yeonwoo Kim, Peter Yongho Kim, Yansen Wang, Mingqing Xiao, Dongqi Han, Dongsheng Li, and Taesup Moon. 2026. "Natural Image Autoencoder-Based fMRI Representations for Trait and State Prediction." https://omanscience.com/ar/articles/natural-image-autoencoder-based-fmri-representations-for-trait-and-state-prediction.
هارفارد
Park, J., Kim, Y., Kim, P. Y., Wang, Y., Xiao, M., Han, D., Li, D. and Moon, T. (2026) 'Natural Image Autoencoder-Based fMRI Representations for Trait and State Prediction', Available at: https://omanscience.com/ar/articles/natural-image-autoencoder-based-fmri-representations-for-trait-and-state-prediction.
فانكوفر
Park J, Kim Y, Kim PY, Wang Y, Xiao M, Han D, et al. Natural Image Autoencoder-Based fMRI Representations for Trait and State Prediction. https://omanscience.com/ar/articles/natural-image-autoencoder-based-fmri-representations-for-trait-and-state-prediction
IEEE
J. Park, Y. Kim, P. Y. Kim, Y. Wang, M. Xiao, D. Han, D. Li, and T. Moon, "Natural Image Autoencoder-Based fMRI Representations for Trait and State Prediction," https://omanscience.com/ar/articles/natural-image-autoencoder-based-fmri-representations-for-trait-and-state-prediction.