Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders

• URL: http://arxiv.org/abs/2110.13911v1
• Date: Mon, 25 Oct 2021 11:37:41 GMT
• Title: Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders
• Authors: T. Anderson Keller, Qinghe Gao, Max Welling
• Abstract summary: Category-selectivity describes the observation that certain spatially localized areas of the cerebral cortex tend to respond robustly and selectively to stimuli from specific limited categories. We leverage the newly introduced Topographic Variational Autoencoder to model of the emergence of such localized category-selectivity in an unsupervised manner. We show preliminary results suggesting that our model yields a nested spatial hierarchy of increasingly abstract categories, analogous to observations from the human ventral temporal cortex.
• Score: 72.15087604017441
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Category-selectivity in the brain describes the observation that certain spatially localized areas of the cerebral cortex tend to respond robustly and selectively to stimuli from specific limited categories. One of the most well known examples of category-selectivity is the Fusiform Face Area (FFA), an area of the inferior temporal cortex in primates which responds preferentially to images of faces when compared with objects or other generic stimuli. In this work, we leverage the newly introduced Topographic Variational Autoencoder to model of the emergence of such localized category-selectivity in an unsupervised manner. Experimentally, we demonstrate our model yields spatially dense neural clusters selective to faces, bodies, and places through visualized maps of Cohen's d metric. We compare our model with related supervised approaches, namely the TDANN, and discuss both theoretical and empirical similarities. Finally, we show preliminary results suggesting that our model yields a nested spatial hierarchy of increasingly abstract categories, analogous to observations from the human ventral temporal cortex.

Related papers

• Optimizing contrastive learning for cortical folding pattern detection [0.0]
  We build a self-supervised deep learning model to detect folding patterns in the cingulate region. This is the first time that a self-supervised deep learning model has been applied to cortical skeletons on such a large dataset.
  arXiv  Detail & Related papers  (2024-01-31T17:59:57Z)
• Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models [6.866437017874623]
  We introduce a data-driven approach in which we synthesize images predicted to activate a given brain region using paired natural images and fMRI recordings. Our approach builds on recent generative methods by combining large-scale diffusion models with brain-guided image synthesis. These results advance our understanding of the fine-grained functional organization of human visual cortex.
  arXiv  Detail & Related papers  (2023-06-05T17:59:05Z)
• Learning disentangled representations for explainable chest X-ray classification using Dirichlet VAEs [68.73427163074015]
  This study explores the use of the Dirichlet Variational Autoencoder (DirVAE) for learning disentangled latent representations of chest X-ray (CXR) images. The predictive capacity of multi-modal latent representations learned by DirVAE models is investigated through implementation of an auxiliary multi-label classification task.
  arXiv  Detail & Related papers  (2023-02-06T18:10:08Z)
• Distinguishing representational geometries with controversial stimuli: Bayesian experimental design and its application to face dissimilarity judgments [0.5735035463793008]
  We show that a neural network trained to invert a 3D-face-model graphics is more human-aligned than the same architecture trained on identification, classification, or autoencoding. Our results indicate that a neural network trained to invert a 3D-face-model graphics is more human-aligned than the same architecture trained on identification, classification, or autoencoding.
  arXiv  Detail & Related papers  (2022-11-28T04:17:35Z)
• Domain Adaptive Nuclei Instance Segmentation and Classification via Category-aware Feature Alignment and Pseudo-labelling [65.40672505658213]
  We propose a novel deep neural network, namely Category-Aware feature alignment and Pseudo-Labelling Network (CAPL-Net) for UDA nuclei instance segmentation and classification. Our approach outperforms state-of-the-art UDA methods with a remarkable margin.
  arXiv  Detail & Related papers  (2022-07-04T07:05:06Z)
• Brain Cortical Functional Gradients Predict Cortical Folding Patterns via Attention Mesh Convolution [51.333918985340425]
  We develop a novel attention mesh convolution model to predict cortical gyro-sulcal segmentation maps on individual brains. Experiments show that the prediction performance via our model outperforms other state-of-the-art models.
  arXiv  Detail & Related papers  (2022-05-21T14:08:53Z)
• Self-Supervised Graph Representation Learning for Neuronal Morphologies [75.38832711445421]
  We present GraphDINO, a data-driven approach to learn low-dimensional representations of 3D neuronal morphologies from unlabeled datasets. We show, in two different species and across multiple brain areas, that this method yields morphological cell type clusterings on par with manual feature-based classification by experts. Our method could potentially enable data-driven discovery of novel morphological features and cell types in large-scale datasets.
  arXiv  Detail & Related papers  (2021-12-23T12:17:47Z)
• Attention-gating for improved radio galaxy classification [0.0]
  We introduce attention as a state of the art mechanism for classification of radio galaxies using convolutional neural networks. We show how the selection of normalisation and aggregation methods used in attention-gating can affect the output of individual models. The resulting attention maps can be used to interpret the classification choices made by the model.
  arXiv  Detail & Related papers  (2020-12-02T14:49:53Z)
• Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation [71.59275788106622]
  We propose to learn the underlying class-agnostic commonalities that can be generalized from mask-annotated categories to novel categories. Our model significantly outperforms the state-of-the-art methods on both partially supervised setting and few-shot setting for instance segmentation on COCO dataset.
  arXiv  Detail & Related papers  (2020-07-24T07:23:44Z)
• Gaussian-Dirichlet Random Fields for Inference over High Dimensional Categorical Observations [3.383942690870476]
  We propose a generative model for the distribution of high dimensional categorical observations produced by robots. The proposed approach combines the use of Dirichlet distributions to sparse co-occurrence relations between the observed categories.
  arXiv  Detail & Related papers  (2020-03-26T19:29:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.