A differentiable Gaussian Prototype Layer for explainable Segmentation
- URL: http://arxiv.org/abs/2306.14361v1
- Date: Sun, 25 Jun 2023 22:33:21 GMT
- Title: A differentiable Gaussian Prototype Layer for explainable Segmentation
- Authors: Michael Gerstenberger, Steffen Maa{\ss}, Peter Eisert, Sebastian Bosse
- Abstract summary: We introduce a gradient-based prototype layer for gradient-based prototype learning.
We show it can be used as a novel building block for explainable neural networks.
- Score: 3.258592531141818
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We introduce a Gaussian Prototype Layer for gradient-based prototype learning
and demonstrate two novel network architectures for explainable segmentation
one of which relies on region proposals. Both models are evaluated on
agricultural datasets. While Gaussian Mixture Models (GMMs) have been used to
model latent distributions of neural networks before, they are typically fitted
using the EM algorithm. Instead, the proposed prototype layer relies on
gradient-based optimization and hence allows for end-to-end training. This
facilitates development and allows to use the full potential of a trainable
deep feature extractor. We show that it can be used as a novel building block
for explainable neural networks. We employ our Gaussian Prototype Layer in (1)
a model where prototypes are detected in the latent grid and (2) a model
inspired by Fast-RCNN with SLIC superpixels as region proposals. The earlier
achieves a similar performance as compared to the state-of-the art while the
latter has the benefit of a more precise prototype localization that comes at
the cost of slightly lower accuracies. By introducing a gradient-based GMM
layer we combine the benefits of end-to-end training with the simplicity and
theoretical foundation of GMMs which will allow to adapt existing
semi-supervised learning strategies for prototypical part models in future.
Related papers
- Language Models are Graph Learners [70.14063765424012]
Language Models (LMs) are challenging the dominance of domain-specific models, including Graph Neural Networks (GNNs) and Graph Transformers (GTs)
We propose a novel approach that empowers off-the-shelf LMs to achieve performance comparable to state-of-the-art GNNs on node classification tasks.
arXiv Detail & Related papers (2024-10-03T08:27:54Z) - Split-and-Fit: Learning B-Reps via Structure-Aware Voronoi Partitioning [50.684254969269546]
We introduce a novel method for acquiring boundary representations (B-Reps) of 3D CAD models.
We apply a spatial partitioning to derive a single primitive within each partition.
We show that our network, coined NVD-Net for neural Voronoi diagrams, can effectively learn Voronoi partitions for CAD models from training data.
arXiv Detail & Related papers (2024-06-07T21:07:49Z) - A Deep Dive into the Connections Between the Renormalization Group and
Deep Learning in the Ising Model [0.0]
Renormalization group (RG) is an essential technique in statistical physics and quantum field theory.
We develop extensive renormalization techniques for the 1D and 2D Ising model to provide a baseline for comparison.
For the 2D Ising model, we successfully generated Ising model samples using the Wolff algorithm, and performed the group flow using a quasi-deterministic method.
arXiv Detail & Related papers (2023-08-21T22:50:54Z) - Cramer Type Distances for Learning Gaussian Mixture Models by Gradient
Descent [0.0]
As of today, few known algorithms can fit or learn Gaussian mixture models.
We propose a distance function called Sliced Cram'er 2-distance for learning general multivariate GMMs.
These features are especially useful for distributional reinforcement learning and Deep Q Networks.
arXiv Detail & Related papers (2023-07-13T13:43:02Z) - A Hybrid of Generative and Discriminative Models Based on the
Gaussian-coupled Softmax Layer [5.33024001730262]
We propose a method to train a hybrid of discriminative and generative models in a single neural network.
We demonstrate that the proposed hybrid model can be applied to semi-supervised learning and confidence calibration.
arXiv Detail & Related papers (2023-05-10T05:48:22Z) - Rethinking Semantic Segmentation: A Prototype View [126.59244185849838]
We present a nonparametric semantic segmentation model based on non-learnable prototypes.
Our framework yields compelling results over several datasets.
We expect this work will provoke a rethink of the current de facto semantic segmentation model design.
arXiv Detail & Related papers (2022-03-28T21:15:32Z) - A new perspective on probabilistic image modeling [92.89846887298852]
We present a new probabilistic approach for image modeling capable of density estimation, sampling and tractable inference.
DCGMMs can be trained end-to-end by SGD from random initial conditions, much like CNNs.
We show that DCGMMs compare favorably to several recent PC and SPN models in terms of inference, classification and sampling.
arXiv Detail & Related papers (2022-03-21T14:53:57Z) - Generation Drawing/Grinding Trajectoy Based on Hierarchical CVAE [4.817429789586127]
We propose a method to model the local and global features of the drawing/grinding trajectory with hierarchical Variational Autoencoders (VAEs)
The hierarchical generation network enables the generation of higher-order trajectories with a relatively small amount of training data.
It is possible to generate new trajectories, which have never been learned in the past, by changing the combination of the learned models.
arXiv Detail & Related papers (2021-11-22T02:40:06Z) - Mix Dimension in Poincar\'{e} Geometry for 3D Skeleton-based Action
Recognition [57.98278794950759]
Graph Convolutional Networks (GCNs) have already demonstrated their powerful ability to model the irregular data.
We present a novel spatial-temporal GCN architecture which is defined via the Poincar'e geometry.
We evaluate our method on two current largest scale 3D datasets.
arXiv Detail & Related papers (2020-07-30T18:23:18Z) - Binarized Graph Neural Network [65.20589262811677]
We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters.
Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches.
Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
arXiv Detail & Related papers (2020-04-19T09:43:14Z)
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.