arXiv:2606. 03118v1 Announce Type: new Abstract: Objective: Diseases such as age-related macular degeneration and retinitis pigmentosa cause the degradation of the photoreceptor layer.
arXiv:2610.17154v2 Announce Type: replace-cross Abstract: Decoding visual stimuli from the spiking activity of retinal ganglion cells (RGCs) informs both our understanding of the retinal code and the...
FoAViS is a foveated active vision system that samples visual input using a log‑polar foveation and stores information in a 2D spatial memory. The system’s fixation policy is trained concurrently with tasks such as classification and semantic segmentation, allowing the same memory to be read out globally or densely without architectural changes. Learned fixation policies outperform non‑learned heuristics, improving task performance and producing scanpaths that resemble human gaze behavior.
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...
Brain-to-image retrieval seeks to identify the visual stimulus that elicited a non-invasive neural response. Candidate images are typically represented by pretrained vision models, whose internal repr...
arXiv:2603. 18846v3 Announce Type: replace-cross Abstract: Foundation models are used to extract transferable representations from large amounts of unlabeled data, typically via self-supervised learning (SSL).
OptiModNet is a lightweight UNet‑Transformer hybrid designed for optic disc and cup segmentation. It incorporates grouped‑query and channel attention across multiple stages, along with an Aggregated Pyramid Loss to improve gradient flow and structural consistency. Evaluated on the REFUGE2 dataset, it surpasses existing methods by over 2.5 % while using only 3.73 GFLOPs and 1.93 M parameters.
The paper introduces the Dormant Spiking Neuron (DSN), a state-driven mechanism that allows neurons in spiking neural networks to enter a dormant state when their membrane potential falls below a negative threshold. This dynamic gating prunes redundant computations at the instance level and is trained end‑to‑end via backpropagation through time with surrogate gradients. Experiments on static and neuromorphic datasets, including ImageNet, show that DSN reduces computational energy by 40% to over 70% and improves baseline SNN accuracy by 1.34%, outperforming state‑of‑the‑art static pruning methods.
arXiv:2609.36391v1 Announce Type: cross Abstract: An ongoing challenge in sensory neuroscience is to characterize the feature dimensions encoded by cortical populations. Recent approaches probe featu...
The paper proposes a method for distilling a vision‑based policy from a state‑based teacher policy in laparoscopic robotic manipulation. By using privileged state observations as a teacher, the vision policy learns from RGB images and proprioception, requiring fewer expert demonstrations than imitation learning and outperforming pure reinforcement learning. Experiments in simulation show that this distillation approach yields more consistent and stable performance across various surgical tasks.
arXiv:2607. 16295v1 Announce Type: cross Abstract: Mechanistic interpretability has made significant strides in understanding neural network representations, with sparse dictionary learning (SDL) methods, most prominently sparse autoencoders, as a central paradigm.
arXiv:2610.33340v1 Announce Type: new Abstract: Vision foundation models for retinal imaging are large and computationally demanding, limiting point-of-care deployment. We ask how much of such a mode...
arXiv:2607. 29337v1 Announce Type: cross Abstract: Background and Objective: Generating realistic medical images with anatomically accurate segmentation masks helps address the shortage of annotated data in medical imaging, particularly in optical coherence tomography (OCT) of mouse eyes, where manual retinal layer delineation is labour-intensive due to tiny structures and required expertise, resulting in scarce datasets.