arXiv Computer Vision

A probabilistic model of visual segmentation explains early visual cortical dynamics

The paper presents a biologically plausible model of visual cortex computation that couples feature inference with segmentation inference, generating neural dynamics through iterative recurrence and feedback. The model predicts gain and variability changes in evoked responses to natural images and reproduces classic single‑neuron findings such as gain dynamics and variability decay during stimulus presentation. It further suggests that these dynamics are organized around inferred segment structure and are more heterogeneous than previously thought, offering a normative framework that could inform both experimental and artificial network designs.

arXiv AI
Oct 28

Inferring Inference

The paper proposes a mathematical framework to infer canonical distributed computations from large‑scale neural activity. It combines normative assumptions that the brain learns a structured internal model of its environment with an algorithmic view that inference is a nonlinear message‑passing process on a graph‑structured model. Using time‑series neural data from a perceptual inference task, the framework identifies latent variables, their neural representations, the interactions defining the brain’s internal model, and the message functions governing inference, demonstrating its feasibility on simulated neural recordings.

By Rajkumar Vasudeva Raju, Zhe Li, Scott Linderman, Xaq Pitkow
Hugging Face Trending Papers
Jun 3

Coarse-to-fine Hierarchical Architecture with Sequential Mamba for Brain Reconstruction

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.

arXiv AI
Oct 2

Modeling The Object Representations Underlying Human Physical Reasoning

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.

By Andrey Gizdov, Andrea Procopio, Lorenzo Caputi, Georgi I. Ivanov, Yichen Li, Daniel Harari, Tomer Ullman