Feature Visualization

Follow this topic Ask about this topic

Latest papers

8 papers0 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Feature Visualization Recovers Known Cortical Selectivity from TRIBE v2
May 13, 2026Stuart Bladon, Brinnae BentNeural Network Interpretability Visual Neuroscience
Duke University, Durham, NC, USA.
Deep Dreams Are Made of This: Visualizing Monosemantic Features in Diffusion Models
May 6, 2026Adam Szokalski, Mateusz ModrzejewskiDisentangled Representation Learning Latent Diffusion Models
Institute of Computer Science, Warsaw University of Technology, Warsaw, Poland
Adjoint Inversion Reveals Holographic Superposition and Destructive Interference in CNN Classifiers
Apr 30, 2026Kaixiang ShuFeature Superposition Neural Network Interpretability
Independent Researcher · Chongqing, China
Show Me What You Don't Know: Efficient Sampling from Invariant Sets for Model Validation
Mar 23, 2026Armand Rousselot, Joran Wendebourg, Ullrich KötheFeature Visualization Invariant Representation Learning
Computer Vision and Learning Lab, Heidelberg University.
Inverting Neural Networks: New Methods to Generate Neural Network Inputs from Prescribed Outputs
Mar 20, 2026Rebecca Pattichis, Sebastian Janampa, Constantinos S. Pattichis +1Feature Visualization Image Inverse Problems
Department of Electrical Engineering, University of California, Los Angeles, Los Angeles CA, USA · Department of Electrical and Computer Engineering, University of New Mexico, Albuquerque, NM, USA · Department of Computer Science, University of Cyprus, Cyprus
What is Missing? Explaining Neurons Activated by Absent Concepts
Mar 10, 2026Robin Hesse, Simone Schaub-Meyer, Janina Hesse +2Feature Visualization Neural Network Interpretability
Max Planck Institute for Informatics, SIC · Department of Computer Science, Technical University of Darmstadt · Leibniz Institute for Resilience Research +2
Class Visualizations and Activation Atlases for Enhancing Interpretability in Deep Learning-Based Computational Pathology
Mar 7, 2026Marco Gustav, Fabian Wolf, Christina Glasner +6Feature Visualization Explainable Medical Image Analysis
Else Kroener Fresenius Center for Digital Health, Faculty of Medicine, TUD Dresden University of Technology, Dresden, Germany · Institute of Pathology, University Medical Center Mainz, Mainz, Germany · Pathology, Faculty of Medicine, University of Augsburg, Augsburg, Germany +4
Feature Space Analysis by Guided Diffusion Model
Sep 9, 2025Kimiaki Shirahama, Kaduki Yamashita, Miki Yanobu +1Feature Visualization
Department of Information Systems Design, Doshisha University, 1-3 Tatara Miyakodani, Kyotanabe, 610-0394, Kyoto, Japan

May 13, 2026J/K move · Enter open · S save

Feature Visualization Recovers Known Cortical Selectivity from TRIBE v2

Stuart Bladon, Brinnae Bent

Duke University, Durham, NC, USA.

Neural Network Interpretability Visual Neuroscience Feature Visualization Neuroimaging Neural Encoding

Open paper AskPDF arXiv

Brain encoder models predict cortical fMRI responses from the internal activations of pretrained vision and language networks, and are typically evaluated by held-out prediction accuracy. This is a useful signal for training but a poor one for interpretation: it tells us an encoder fits the data without telling us whether it has internalized the functional organization of the brain. We propose feature visualization -- gradient ascent on the encoder's predicted activation for a target region of interest (ROI) -- as a complementary interpretability technique, and apply it to TRIBE v2 composed with V-JEPA 2 (ViT-G, 40 layers), holding both frozen and synthesizing still images for seven regions spanning the ventral and dorsal visual hierarchies. Under identical hyperparameters, the probe recovers a visible progression of increasing spatial scale and feature complexity across V1 to V4, matching the ventral-stream hierarchy. It also produces three distinctive downstream regimes: radial "frozen-motion" streaks for the middle temporal area (MT) despite static-only optimization, face-like features for the fusiform face area (FFA), and consistent rectilinear line patterns for the parahippocampal place area (PPA). Optimized FFA stimuli drive the predicted region ~4x as much as a natural face photograph, consistent with feature visualization producing adversarial super-stimuli rather than canonical exemplars. The probe is simple, differentiable, and applicable to any brain encoder with a differentiable backbone, allowing for qualitative evaluation of brain encoders.