arXiv:2601.21948v2 Announce Type: replace Abstract: Neural visual decoding is a central problem in brain-computer interface research, aiming to reconstruct human visual perception and to elucidate th...
arXiv:2606. 28399v1 Announce Type: cross Abstract: The structure of human visual representations underpins our capacity for adaptive behaviour.
The study explores how to fine‑tune visual brain encoding models so that their internal representations better match individual human perceptual similarity judgments. Using similarity data from 100 images collected from eight participants in the Natural Scenes Dataset, the authors adapted a generic similarity model (DreamSim) to create personalized perceptual similarity models for each subject. They then fine‑tuned each participant’s baseline encoder with either generic or personalized similarity information, finding that models trained with personalized judgments were most aligned with human perceptual similarity and preserved inter‑subject correlations of those judgments.
arXiv:2603. 13994v2 Announce Type: replace-cross Abstract: Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties.
The study investigates how vision models represent objects compared to humans during physical reasoning tasks. By comparing segmentation outputs from several architectures (DINOv2, SegFormer, DeepLabV3+, UPerNet) to human behavior in time‑to‑collision and change‑detection tasks, the authors find that briefly trained models are too coarse, fully trained models are too fine, and an intermediate training stage best matches the coarse, volumetric bodies humans use. Larger models reach this intermediate alignment earlier, suggesting that resource constraints drive the emergence of human‑like representations in general‑purpose vision systems.
arXiv:2605.13675v2 Announce Type: replace-cross Abstract: Deep neural networks trained with different architectures, objectives, and datasets have been reported to converge on similar visual represen...
arXiv:2610.06896v1 Announce Type: new Abstract: Frontier multimodal large language models (MLLMs) are increasingly positioned as general purpose visual reasoners as part of the quest for artificial g...
The paper presents a quantitative study of how well the attention maps of CNNs, Vision Transformers, and Vision Mamba align with human visual perception, using eye‑tracking data as ground truth. A standardized normalization pipeline maps attribution maps and gaze heatmaps to spatial probability distributions, and alignment is measured with Jensen‑Shannon similarity, Chi‑square similarity, and Pearson correlation across fine‑grained classification, medical imaging, and emotion recognition tasks. Results show that CNNs exhibit more global, diffuse saliency that generally matches human perception, ViTs focus on fine‑grained, patch‑level features, and Vision Mamba performs well in medical tasks but diverges in natural images, with architectural and training choices affecting interpretability.
CoreDNA is an unsupervised, task‑agnostic coreset selection method that uses neuron activations from vision foundation models to build per‑image and per‑dataset distributions. By comparing each image’s distribution to the overall dataset distribution, it captures both low‑level visual structure and high‑level semantic information across layers, identifying high‑quality samples in the tails of the last layer’s activation statistics. The method achieves state‑of‑the‑art performance across image classification, semantic segmentation, depth estimation, and imitation learning for driving and mobile manipulation, demonstrating broad generalization without task‑specific tailoring.
arXiv:2607. 18625v1 Announce Type: cross Abstract: Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones.
Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones. However, MambaOut demonstrates that a Gated CNN block can match or exceed VMamba on image classification, questioning the necessity of SSMs for vision.
arXiv:2610.27770v1 Announce Type: new Abstract: Artificial intelligence systems are increasingly deployed in high-stakes decision-making. In response, prototype-based models in explainable AI have at...