A neural-anchor-based retrieval framework that treats the high-repetition center as an anchor and approaches it from both sides: a denoiser pulls the noisy query toward the true anchor, and a small network predicts each candidate's pseudo anchor from its image and pulls the image toward it.
Abstract
Decoding visual information from brain signals probes neural representations and enables neuro-rehabilitation and dream decoding. Recent brain-to-image retrieval approaches have achieved promising performance, typically by averaging many (up to 80) neural trials per image, requiring repeated stimulus presentation that increases latency, cost, and user burden. When only one or a few repetitions are available, the retrieval accuracy drops sharply. This drop is commonly attributed to query noise because averaging suppresses noise and increases signal stability. However, we find a non-transitive alignment pattern: the low-repetition query signal and the image representation each align with the high-repetition center, but not directly with each other. This pattern shows that query noise is only part of the problem and that gallery placement also affects retrieval. We therefore propose a neural-anchor-based retrieval (NEAR) framework that treats the high-repetition center as an anchor and approaches it from both sides: a denoiser pulls the noisy query toward the true anchor, and a small network predicts each candidate's pseudo anchor from its image and pulls the image toward it. Across four datasets spanning EEG, MEG and fMRI, NEAR consistently improved retrieval in the few-repetition regime. On THINGS-EEG2, it improved 200-way Top-1 accuracy by 5.7 and 9.3 percentage points respectively, when averaging one and four repetitions. By anchoring neural and visual representations, NEAR reduces reliance on repeated acquisition and brings neural retrieval closer to real-world deployment.
NeuroGlyph, which learns a trial-independent visual target from multiple depths of a frozen visual backbone, achieves the strongest system-level performance in six of eight reported metrics, and support learning retrieval targets across the visual hierarchy rather than prescribing one visual depth.
Ye Wang, Hao-Kun Ren, Hong Yu et al.· arXiv.org· 1 citation
By aligning EEG with layer-wise neural visibility rather than fixed high-level semantics, the proposed framework improves both retrieval accuracy and image reconstruction in EEG-based visual decoding.
BrainFocus is proposed, a reliable EEG-guided efficient VLM framework for VQA that improves VQA accuracy and demonstrates that EEG can guide efficient VLM inference even when its semantic decoding is imperfect.
Together, these findings provide a comprehensive neural model of ensemble perception, demonstrating that the brain constructs abstract summary statistics through a temporally ordered, spectrally specific transformation that balances sensory fidelity with representational abstraction.
Qing Kong, Yu-Qing Zhao, Fang Fang et al.· Journal of Neuroscience· 0 citations
This work examines two representative architectures, MAtt and GBWAtt, and finds that their learned attention weights remain close to uniform after training, and introduces SPD-MetaFormer, an attention-free architecture built on uniformly weighted Fr\'echet aggregation under log-Euclidean geometry.
Many vision applications ask several independent, forced-choice questions about the same image. Visual Jev encodes the image and public context once, executes isolated question suffixes as a batch, and reads candidate probabilities from the backbone's language-model head. Across four benchmarks, answer-supervised post-...