arXiv:2609.24136v1 Announce Type: new Abstract: Brain-to-image retrieval seeks to identify the visual stimulus that elicited a non-invasive neural response. Candidate images are typically represented...
arXiv:2606. 00121v1 Announce Type: cross Abstract: Reconstructing visual stimuli from brain recordings has been a meaningful and challenging task in brain decoding.
Understanding the relationship between deep visual representations and the human visual system is a fundamental challenge in computational neuroscience. While modern vision models achieve strong performance in image recognition, their correspondence with the hierarchical organization of the human visual cortex remains an open question.
The paper presents a reproducible single‑subject baseline for reconstructing visual stimuli from EEG using a temporal‑spatial convolutional encoder that maps averaged EEG signals to 512‑dimensional ViT-B/32 image features. On the THINGS‑EEG2 dataset, the model achieves 12.83%, 39.17%, and 58.00% image recall at ranks 1, 5, and 10, respectively, outperforming analytical chance levels. The study also shows that performance drops sharply when applying a model trained on one subject to others, and that direct conditional generators without external visual weights produce noise‑dominated outputs, indicating that only coarse semantic decoding is feasible under the tested protocol.
arXiv:2606. 04772v1 Announce Type: cross Abstract: Understanding the relationship between deep visual representations and the human visual system is a fundamental challenge in computational neuroscience.
The paper introduces NEAR, a neural-anchor-based retrieval framework that improves brain-to-image retrieval when only a few neural trials are available. By treating a high‑repetition center as an anchor, NEAR uses a denoiser to pull noisy queries toward the anchor and a small network to predict pseudo anchors for candidate images, thereby aligning both neural and visual representations. Experiments on EEG, MEG, and fMRI datasets show consistent gains, including a 5.7–9.3 percentage point improvement in 200‑way Top‑1 accuracy on THINGS‑EEG2 with only one or four repetitions.
The paper introduces an adaptive cortically constrained method for aligning EEG signals with visual representations in zero‑shot brain‑to‑image retrieval. It reconstructs EEG into ROI‑level source patterns, encodes them with a Neuro‑ROI Attention Encoder, and applies evidence‑based adaptive visual supervision to account for response‑wise variability. On the THINGS‑EEG dataset, the approach achieves strong 200‑way retrieval performance and offers ROI‑level attribution for interpretability.
The paper introduces NEAR, a neural‑anchor‑based retrieval framework that improves brain‑to‑image retrieval when only a few neural trials are available. By treating the high‑repetition center as an anchor, a denoiser pulls noisy queries toward it while a small network predicts pseudo anchors for candidate images, aligning both neural and visual representations. Across EEG, MEG, and fMRI datasets, NEAR consistently boosts retrieval accuracy, notably raising 200‑way Top‑1 accuracy on THINGS‑EEG2 by 5.7–9.3 percentage points with just one to four repetitions.
arXiv:2608. 20810v1 Announce Type: cross Abstract: Multimodal information systems increasingly route generated visual content back through the same vision-language index that informed its production, so the output must remain retrievable by the queries it was meant to serve.
The paper introduces CERES, a closed‑loop multimodal indexing framework that addresses semantic collapse in multimodal generation by building a three‑level semantic pyramid and using scale‑routed cross‑attention to generate images that remain retrievable by their original queries. CERES employs a co‑occurrence‑aware router, a lightweight U‑Net generator, and a soft‑Jaccard coverage objective to ensure generated images cover the intended concepts, verified by re‑indexing with a frozen vision‑language model and an external DINOv2 probe. Experiments on four pansharpening benchmarks show state‑of‑the‑art performance, especially under extreme scale variation, and significant improvements in concept‑query retrieval and image‑text ranking metrics.
SCORE: Subject Coordinate Recovery for Label-Free Cross-Subject EEG-to-Image Retrieval proposes a new framework that aligns EEG signals from different subjects into a common image space without requiring labeled calibration data. By training on source subjects and estimating an orthogonal transformation at deployment, SCORE recovers target EEG coordinates and selects reliable EEG-image landmarks through hubness-corrected matching. The method achieves state‑of‑the‑art Top‑1/Top‑5 accuracy on two public benchmarks, outperforming existing baselines by significant margins.
PailitaoGR is a generative image retrieval method that incorporates target-focused perception and selective auxiliary-evidence utilization. It uses a target Enhancer and on-policy distillation to highlight search-target regions, and an auxiliary enhancer with incremental contrastive distillation to exploit auxiliary evidence. Trained on real-world online image-search logs, it achieves an average 13.8% improvement over existing baselines.