Safety
AlignedCut: Visual Concepts Discovery on Brain-Guided Universal Feature Space
arXiv:2406.18344v2 Announce Type: replace Abstract: We study the intriguing connection between visual data, deep networks, and the brain. Our method creates a universal channel alignment by using brai
arXiv:2406.18344v2 Announce Type: replace Abstract: We study the intriguing connection between visual data, deep networks, and the brain. Our method creates a universal channel alignment by using brain voxel fMRI response prediction as the training objective. We discover that deep networks, trained with different objectives, share common feature channels across various models. These channels can be clustered into recurring sets, corresponding to distinct brain regions, indicating the formation of visual concepts. Tracing the clusters of channel responses onto the images, we see semantically meaningful object segments emerge, even without any supervised decoder. Furthermore, the universal feature alignment and the clustering of channels produce a picture and quantification of how visual information is processed through the different network layers, which produces precise comparisons between the networks.
Related
- LINE: LLM-based Iterative Neuron Explanations for Vision Models
- Brain-Grasp: Graph-based Saliency Priors for Improved fMRI-based Visual Brain Decoding
- Brain-DiT: A Universal Multi-state fMRI Foundation Model with Metadata-Conditioned Pretraining
- Multi-Modal Learning meets Genetic Programming: Analyzing Alignment in Latent Space Optimization
Source: arXiv cs.CV | 2026-04-22