Learning Entropy and Spatial Adaptation Dynamics of Multilayer Perceptrons for Structural Point Extraction

• URL: http://arxiv.org/abs/2606.10170v1
• Date: Mon, 08 Jun 2026 21:05:03 GMT
• Title: Learning Entropy and Spatial Adaptation Dynamics of Multilayer Perceptrons for Structural Point Extraction
• Abstract summary: This paper extends the concept of Learning Entropy (LE) from temporal adaptive systems to spatial learning in multilayer spatial networks (MLPs)<n>An is trained to predict the intensity of a center pixel from its surrounding spatial context, while LE is evaluated from the incremental adaptation of neural weights during learning across image-derived samples.<n>The Spatial Learning Entropy Maps (SLEM) identify unusual image points and regions that induce strong adaptation of the neural network and therefore have an important role in the learning process.
• Score: 1.4681690787310104
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper extends the concept of Learning Entropy (LE) from temporal adaptive systems to spatial learning in multilayer perceptron networks (MLPs) applied to image data. Instead of evaluating image structure directly from gradients or covariance operators, as local neighborhood methods do, the proposed approach analyzes the learning process itself through Learning Entropy. An MLP is trained to predict the intensity of a center pixel from its surrounding spatial context, while LE is evaluated from the incremental adaptation of neural weights during learning across image-derived samples. The resulting Spatial Learning Entropy Maps (SLEM) identify unusual image points and regions that induce strong adaptation of the neural network and therefore have an important role in the learning process. The results indicate that spatial Learning Entropy provides a complementary perspective to conventional feature extraction and explainability methods by highlighting spatial locations that are particularly informative for network learning. Spatial Learning Entropy provides a complementary perspective to conventional feature extraction and explainability methods by identifying image points and regions according to their learning impact rather than their local structural properties. The proposed framework may open new directions for learning-driven image or scene analysis in computer vision, manufacturing, and robotics.

Related papers

• PointVG-R: Internalizing Geometric Reasoning in MLLMs for Precise Pointing Localization via Visual Chain of Thought [19.680475189691965]
  Pointing-based visual grounding requires models to precisely locate target objects by deciphering complex spatial relationships between the visual scene and pointing gestures.<n>We propose PointVG-R, a reasoning-guided Multi-modal Large Language Model (MLLM)<n>We design a novel geometric reasoning pipeline that simulates the iterative cognitive process humans employ when interpreting pointing gestures.
  arXiv  Detail & Related papers  (2026-06-23T13:06:51Z)
• Learning Entropy Signature for Image Representation and Classification [2.9278915748576826]
  Learning Entropy (LE) has been extended to image analysis through Spatial Learning Entropy Maps (SLEMs)<n>SLEMs are two-dimensional LE distributions that highlight unusually high learning activity across an image.<n>This paper introduces Learning Entropy Signatures (LES), an image descriptor derived from SLEM using the K largest LE locations.
  arXiv  Detail & Related papers  (2026-06-21T18:46:17Z)
• Combi-CAM: A Novel Multi-Layer Approach for Explainable Image Geolocalization [0.5461938536945722]
  We present Combi-CAM, a novel method that enhances the explainability of CNN-based geolocalization models.<n>This approach provides a more detailed understanding of how different image features contribute to the model's decisions.
  arXiv  Detail & Related papers  (2026-03-25T09:29:02Z)
• A Physics-Inspired Deep Learning Framework with Polar Coordinate Attention for Ptychographic Imaging [8.436077464774755]
  Ptychographic imaging confronts inherent challenges in applying deep learning for phase retrieval from diffraction patterns.<n>We present PPN, a physics-inspired deep learning network with Polar Coordinate Attention (PoCA) for ptychographic imaging.
  arXiv  Detail & Related papers  (2024-11-25T06:49:59Z)
• Supervised Learning without Backpropagation using Spike-Timing-Dependent Plasticity for Image Recognition [3.087000217989688]
  This study introduces a novel supervised learning approach for spiking neural networks that does not rely on traditional backpropagation.<n>Instead, it employs spike-timing-dependent plasticity (STDP) within a supervised framework for image recognition tasks.
  arXiv  Detail & Related papers  (2024-10-21T21:32:17Z)
• Masked Contrastive Graph Representation Learning for Age Estimation [44.96502862249276]
  This paper utilizes the property of graph representation learning in dealing with image redundancy information. We propose a novel Masked Contrastive Graph Representation Learning (MCGRL) method for age estimation. Experimental results on real-world face image datasets demonstrate the superiority of our proposed method over other state-of-the-art age estimation approaches.
  arXiv  Detail & Related papers  (2023-06-16T15:53:21Z)
• Reparameterization through Spatial Gradient Scaling [69.27487006953852]
  Reparameterization aims to improve the generalization of deep neural networks by transforming convolutional layers into equivalent multi-branched structures during training. We present a novel spatial gradient scaling method to redistribute learning focus among weights in convolutional networks.
  arXiv  Detail & Related papers  (2023-03-05T17:57:33Z)
• Shap-CAM: Visual Explanations for Convolutional Neural Networks based on Shapley Value [86.69600830581912]
  We develop a novel visual explanation method called Shap-CAM based on class activation mapping. We demonstrate that Shap-CAM achieves better visual performance and fairness for interpreting the decision making process.
  arXiv  Detail & Related papers  (2022-08-07T00:59:23Z)
• Inducing Gaussian Process Networks [80.40892394020797]
  We propose inducing Gaussian process networks (IGN), a simple framework for simultaneously learning the feature space as well as the inducing points. The inducing points, in particular, are learned directly in the feature space, enabling a seamless representation of complex structured domains. We report on experimental results for real-world data sets showing that IGNs provide significant advances over state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-21T05:27:09Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty [91.0564497403256]
  We present a novel framework that involves probabilistic fusion between the two families of predictions during network training. Our network features a self-attention graph neural network, which drives the learning by enforcing strong interactions between different correspondences. We propose motion parmeterizations suitable for learning and show that our method achieves state-of-the-art performance on the challenging DeMoN and ScanNet datasets.
  arXiv  Detail & Related papers  (2021-04-16T17:59:06Z)
• Model-inspired Deep Learning for Light-Field Microscopy with Application to Neuron Localization [27.247818386065894]
  We propose a model-inspired deep learning approach to perform fast and robust 3D localization of sources using light-field microscopy images. This is achieved by developing a deep network that efficiently solves a convolutional sparse coding problem. Experiments on localization of mammalian neurons from light-fields show that the proposed approach simultaneously provides enhanced performance, interpretability and efficiency.
  arXiv  Detail & Related papers  (2021-03-10T16:24:47Z)
• Variational Structured Attention Networks for Deep Visual Representation Learning [49.80498066480928]
  We propose a unified deep framework to jointly learn both spatial attention maps and channel attention in a principled manner. Specifically, we integrate the estimation and the interaction of the attentions within a probabilistic representation learning framework. We implement the inference rules within the neural network, thus allowing for end-to-end learning of the probabilistic and the CNN front-end parameters.
  arXiv  Detail & Related papers  (2021-03-05T07:37:24Z)

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.