# SATTC: Structure-Aware Label-Free Test-Time Calibration for Cross-Subject EEG-to-Image Retrieval

arXiv: https://arxiv.org/abs/2603.20738 · HTML: https://mlsanity.com/paper/2603.20738/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 31 references that are in the map.
- First posted on arXiv 21 Mar 2026.

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Offline bilingual word vectors, orthogonal transformations and the inverted softmax](https://mlsanity.com/paper/1702.03859/) (2017)
- [Decoding Natural Images from EEG for Object Recognition](https://mlsanity.com/paper/2308.13234/) (2023)
- [Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion](https://mlsanity.com/paper/2403.07721/) (2024)
- [Deep Learning Human Mind for Automated Visual Classification](https://mlsanity.com/paper/1609.00344/) (2016)
- [Improving zero-shot learning by mitigating the hubness problem](https://mlsanity.com/paper/1412.6568/) (2014)
- [Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations](https://mlsanity.com/paper/1611.05113/) (2016)
- [Ridge Regression, Hubness, and Zero-Shot Learning](https://mlsanity.com/paper/1507.00825/) (2015)
- [MS-MDA: Multisource Marginal Distribution Adaptation for Cross-subject and Cross-session EEG Emotion Recognition](https://mlsanity.com/paper/2107.07740/) (2021)
- [Mind's Eye: Image Recognition by EEG via Multimodal Similarity-Keeping Contrastive Learning](https://mlsanity.com/paper/2406.16910/) (2024)
- [NECOMIMI: Neural-Cognitive Multimodal EEG-informed Image Generation with Diffusion Models](https://mlsanity.com/paper/2410.00712/) (2024)
- [Cross-Subject Statistical Shift Estimation for Generalized Electroencephalography-based Mental Workload Assessment](https://mlsanity.com/paper/1906.08823/) (2019)
- [Category-aware EEG image generation based on wavelet transform and contrast semantic loss](https://mlsanity.com/paper/2505.24301/) (2025)

## Built on by (most cited first, 3 of 3)

- [SCORE: Subject Coordinate Recovery for Label-Free Cross-Subject EEG-to-Image Retrieval](https://mlsanity.com/paper/2608.19134/) (2026)
- [RPA: Residual Patch-Token Adapter for Image Retrieval from EEG and MEG](https://mlsanity.com/paper/2609.31698/) (2026)
- [Structured Visual Target Learning For Cross-Subject eeg-to-image retrieval](https://mlsanity.com/paper/2609.36971/) (2026)

## Abstract (arXiv)

Cross-subject EEG-to-image retrieval for visual decoding is challenged by subject shift and hubness in the embedding space, which distort similarity geometry and destabilize top-k rankings, making small-k shortlists unreliable. We introduce SATTC (Structure-Aware Test-Time Calibration), a label-free calibration head that operates directly on the similarity matrix of frozen EEG and image encoders. SATTC combines a geometric expert, subject-adaptive whitening of EEG embeddings with an adaptive variant of Cross-domain Similarity Local Scaling (CSLS), and a structural expert built from mutual nearest neighbors, bidirectional top-k ranks, and class popularity, fused via a simple Product-of-Experts rule. On THINGS-EEG2 under a strict leave-one-subject-out protocol, standardized inference with cosine similarities, L2-normalized embeddings, and candidate whitening already yields a strong cross-subject baseline over the original ATM retrieval setup. Building on this baseline, SATTC further improves Top-1 and Top-5 accuracy, reduces hubness and per-class imbalance, and produces more reliable small-k shortlists. These gains transfer across multiple EEG encoders, supporting SATTC as an encoder-agnostic, label-free test-time calibration layer for cross-subject neural decoding.