HyFI: Hyperbolic Feature Interpolation for Brain-Vision Alignment

• URL: http://arxiv.org/abs/2603.22721v1
• Date: Tue, 24 Mar 2026 02:35:54 GMT
• Title: HyFI: Hyperbolic Feature Interpolation for Brain-Vision Alignment
• Abstract summary: We propose a novel framework, Hyperbolic Feature Interpolation (HyFI), which interpolates between semantic and perceptual visual features along hyperbolic geodesics.<n>HyFI achieves state-of-the-art performance in zero-shot brain-to-image retrieval, outperforming prior methods with Top-1 accuracy improvements of up to +17.3%.
• Score: 12.235537797397798
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent progress in artificial intelligence has encouraged numerous attempts to understand and decode human visual system from brain signals. These prior works typically align neural activity independently with semantic and perceptual features extracted from images using pre-trained vision models. However, they fail to account for two key challenges: (1) the modality gap arising from the natural difference in the information level of representation between brain signals and images, and (2) the fact that semantic and perceptual features are highly entangled within neural activity. To address these issues, we utilize hyperbolic space, which is well-suited for considering differences in the amount of information and has the geometric property that geodesics between two points naturally bend toward the origin, where the representational capacity is lower. Leveraging these properties, we propose a novel framework, Hyperbolic Feature Interpolation (HyFI), which interpolates between semantic and perceptual visual features along hyperbolic geodesics. This enables both the fusion and compression of perceptual and semantic information, effectively reflecting the limited expressiveness of brain signals and the entangled nature of these features. As a result, it facilitates better alignment between brain and visual features. We demonstrate that HyFI achieves state-of-the-art performance in zero-shot brain-to-image retrieval, outperforming prior methods with Top-1 accuracy improvements of up to +17.3% on THINGS-EEG and +9.1% on THINGS-MEG.

Related papers

• Brain-Inspired Capture: Evidence-Driven Neuromimetic Perceptual Simulation for Visual Decoding [28.75188553928776]
  Brain-Inspired Capture (BI-Cap) is a neuromimetic perceptual simulation paradigm that aligns neural and visual modalities.<n>BI-Cap substantially outperforms state-of-the-art methods, achieving relative gains of 9.2% and 8.0%, respectively.
  arXiv  Detail & Related papers  (2026-04-20T08:07:33Z)
• Learning Brain Representation with Hierarchical Visual Embeddings [30.701493890961284]
  We propose a brain-image alignment strategy that leverages pre-trained visual encoders with distinct inductive biases to capture hierarchical and multi-scale visual representations.<n>Our method achieves a favorable balance between retrieval accuracy and reconstruction fidelity.
  arXiv  Detail & Related papers  (2026-02-07T11:14:03Z)
• Deep Models, Shallow Alignment: Uncovering the Granularity Mismatch in Neural Decoding [8.822848795081693]
  We propose a novel contrastive learning strategy that aligns neural signals with intermediate representations of visual encoders rather than their final outputs.<n>Our approach effectively unlocks the scaling law in neural visual decoding, enabling decoding performance to scale predictably with the capacity of pre-trained vision backbones.
  arXiv  Detail & Related papers  (2026-01-29T16:30:32Z)
• NeuroCLIP: Brain-Inspired Prompt Tuning for EEG-to-Image Multimodal Contrastive Learning [13.254096454986318]
  We present NeuroCLIP, a prompt tuning framework tailored for EEG-to-image contrastive learning.<n>We are the first to introduce visual prompt tokens into EEG-image alignment, acting as global, modality-level prompts.<n>On the THINGS-EEG2 dataset, NeuroCLIP achieves a Top-1 accuracy of 63.2% in zero-shot image retrieval.
  arXiv  Detail & Related papers  (2025-11-12T12:13:24Z)
• NeuroBridge: Bio-Inspired Self-Supervised EEG-to-Image Decoding via Cognitive Priors and Bidirectional Semantic Alignment [7.860082818617649]
  Visual neural decoding seeks to reconstruct or infer perceived visual stimuli from brain activity patterns.<n>Current approaches remain constrained by the scarcity of high-quality stimulus-brain response pairs.<n>We propose a novel self-supervised architecture, named NeuroBridge, to promote effective cross-modality alignment.
  arXiv  Detail & Related papers  (2025-11-10T08:29:09Z)
• SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning [54.390403684665834]
  Deciphering how visual stimuli are transformed into cortical responses is a fundamental challenge in computational neuroscience.<n>We propose SynBrain, a generative framework that simulates the transformation from visual semantics to neural responses in a probabilistic and biologically interpretable manner.<n> Experimental results demonstrate that SynBrain surpasses state-of-the-art methods in subject-specific visual-to-fMRI encoding performance.
  arXiv  Detail & Related papers  (2025-08-14T03:01:05Z)
• Artificial Kuramoto Oscillatory Neurons [65.16453738828672]
  It has long been known in both neuroscience and AI that ''binding'' between neurons leads to a form of competitive learning where representations are compressed in order to represent more abstract concepts in deeper layers of the network.<n>We introduce Artificial rethinking together with arbitrary connectivity designs such as fully connected convolutional, or attentive mechanisms.<n>We show that this idea provides performance improvements across a wide spectrum of tasks such as unsupervised object discovery, adversarial robustness, uncertainty, quantification, and reasoning.
  arXiv  Detail & Related papers  (2024-10-17T17:47:54Z)
• Disentangled Interaction Representation for One-Stage Human-Object Interaction Detection [70.96299509159981]
  Human-Object Interaction (HOI) detection is a core task for human-centric image understanding. Recent one-stage methods adopt a transformer decoder to collect image-wide cues that are useful for interaction prediction. Traditional two-stage methods benefit significantly from their ability to compose interaction features in a disentangled and explainable manner.
  arXiv  Detail & Related papers  (2023-12-04T08:02:59Z)
• Deep Representations for Time-varying Brain Datasets [4.129225533930966]
  This paper builds an efficient graph neural network model that incorporates both region-mapped fMRI sequences and structural connectivities as inputs. We find good representations of the latent brain dynamics through learning sample-level adaptive adjacency matrices. These modules can be easily adapted to and are potentially useful for other applications outside the neuroscience domain.
  arXiv  Detail & Related papers  (2022-05-23T21:57:31Z)
• An explainability framework for cortical surface-based deep learning [110.83289076967895]
  We develop a framework for cortical surface-based deep learning. First, we adapted a perturbation-based approach for use with surface data. We show that our explainability framework is not only able to identify important features and their spatial location but that it is also reliable and valid.
  arXiv  Detail & Related papers  (2022-03-15T23:16:49Z)
• Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition [49.163326827954656]
  We propose a novel multi-granular-temporal graph network for skeleton-based action classification. We develop a dual-head graph network consisting of two inter-leaved branches, which enables us to extract at least two-temporal resolutions. We conduct extensive experiments on three large-scale datasets.
  arXiv  Detail & Related papers  (2021-08-10T09:25:07Z)
• Rethinking of the Image Salient Object Detection: Object-level Semantic Saliency Re-ranking First, Pixel-wise Saliency Refinement Latter [62.26677215668959]
  We propose a lightweight, weakly supervised deep network to coarsely locate semantically salient regions. We then fuse multiple off-the-shelf deep models on these semantically salient regions as the pixel-wise saliency refinement. Our method is simple yet effective, which is the first attempt to consider the salient object detection mainly as an object-level semantic re-ranking problem.
  arXiv  Detail & Related papers  (2020-08-10T07:12:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.