Continually Learning Structured Visual Representations via Network Refinement with Rerelation

• URL: http://arxiv.org/abs/2502.13935v1
• Date: Wed, 19 Feb 2025 18:18:27 GMT
• Title: Continually Learning Structured Visual Representations via Network Refinement with Rerelation
• Authors: Zeki Doruk Erden, Boi Faltings,
• Abstract summary: Current machine learning paradigm relies on continuous representations like neural networks, which iteratively adjust parameters to approximate outcomes.<n>We propose a method that learns visual space in a structured, continual manner.
• Score: 15.376349115976534
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current machine learning paradigm relies on continuous representations like neural networks, which iteratively adjust parameters to approximate outcomes rather than directly learning the structure of problem. This spreads information across the network, causing issues like information loss and incomprehensibility Building on prior work in environment dynamics modeling, we propose a method that learns visual space in a structured, continual manner. Our approach refines networks to capture the core structure of objects while representing significant subvariants in structure efficiently. We demonstrate this with 2D shape detection, showing incremental learning on MNIST without overwriting knowledge and creating compact, comprehensible representations. These results offer a promising step toward a transparent, continually learning alternative to traditional neural networks for visual processing.

Related papers

• Human-Inspired Continuous Learning of Internal Reasoning Processes: Learning How to Think for Adaptive AI Systems [0.11844977816228043]
  Internal reasoning processes are crucial for developing AI systems capable of sustained adaptation in dynamic real-world environments.<n>We propose a human-inspired continuous learning framework that unifies reasoning, action, reflection, and verification within a sequential reasoning model.
  arXiv  Detail & Related papers  (2026-02-12T03:19:04Z)
• The Imperfect Learner: Incorporating Developmental Trajectories in Memory-based Student Simulation [55.722188569369656]
  This paper introduces a novel framework for memory-based student simulation.<n>It incorporates developmental trajectories through a hierarchical memory mechanism with structured knowledge representation.<n>In practice, we implement a curriculum-aligned simulator grounded on the Next Generation Science Standards.
  arXiv  Detail & Related papers  (2025-11-08T08:05:43Z)
• Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning [58.533203990515034]
  Scaling neural networks has driven breakthrough advances in machine learning, yet this paradigm fails in deep reinforcement learning (DRL)<n>We show that dynamic sparse training strategies provide module-specific benefits that complement the primary scalability foundation established by architectural improvements.<n>We finally distill these insights into Module-Specific Training (MST), a practical framework that exploits the benefits of architectural improvements and demonstrates substantial scalability gains across diverse RL algorithms without algorithmic modifications.
  arXiv  Detail & Related papers  (2025-10-14T03:03:08Z)
• Understanding Learning Dynamics Through Structured Representations [1.7244210453129227]
  This paper investigates how internal structural choices shape the behavior of learning systems.<n>We analyze how these structures influence gradient flow, spectral sensitivity, and fixed-point behavior.<n>Rather than prescribing fixed templates, we emphasize principles of tractable design that can steer learning behavior in interpretable ways.
  arXiv  Detail & Related papers  (2025-08-04T07:15:57Z)
• Embryology of a Language Model [1.1874560263468232]
  In this work, we introduce an embryological approach, applying UMAP to the susceptibility matrix to visualize the model's structural development over training.<n>Our visualizations reveal the emergence of a clear body plan'' charting the formation of known features like the induction circuit and discovering previously unknown structures.
  arXiv  Detail & Related papers  (2025-08-01T05:39:41Z)
• IN45023 Neural Network Design Patterns in Computer Vision Seminar Report, Summer 2025 [0.0]
  This report analyzes the evolution of key design patterns in computer vision by examining six influential papers.<n>We review ResNet, which introduced residual connections to overcome the vanishing gradient problem.<n>We examine the Vision Transformer (ViT), which established a new paradigm by applying the Transformer ar- chitecture to sequences of image patches.
  arXiv  Detail & Related papers  (2025-07-31T09:08:11Z)
• The Importance of Being Lazy: Scaling Limits of Continual Learning [60.97756735877614]
  We show that increasing model width is only beneficial when it reduces the amount of feature learning, yielding more laziness.<n>We study the intricate relationship between feature learning, task non-stationarity, and forgetting, finding that high feature learning is only beneficial with highly similar tasks.
  arXiv  Detail & Related papers  (2025-06-20T10:12:38Z)
• Evolutionary Developmental Biology Can Serve as the Conceptual Foundation for a New Design Paradigm in Artificial Intelligence [15.376349115976534]
  Artificial intelligence (AI) has made significant strides in solving complex tasks.<n>Current neural network-based paradigm, while effective, is heavily constrained by inherent limitations.<n>Recent paradigm shift in evolutionary understanding has been largely overlooked in AI literature.
  arXiv  Detail & Related papers  (2025-06-15T15:41:44Z)
• Agential AI for Integrated Continual Learning, Deliberative Behavior, and Comprehensible Models [15.376349115976534]
  We present the initial design for an AI system, Agential AI (AAI)<n>AAI's core is a learning method that models temporal dynamics with guarantees of completeness, minimality, and continual learning.<n>Preliminary experiments on a simple environment show AAI's effectiveness and potential.
  arXiv  Detail & Related papers  (2025-01-28T13:09:08Z)
• The Cooperative Network Architecture: Learning Structured Networks as Representation of Sensory Patterns [3.9848584845601014]
  We present the cooperative network architecture (CNA), a model that learns such net structure to represent input patterns and deals robustly with noise, deformation, and out-of-distribution data.
  arXiv  Detail & Related papers  (2024-07-08T06:22:10Z)
• Enhancing Generative Class Incremental Learning Performance with Model Forgetting Approach [50.36650300087987]
  This study presents a novel approach to Generative Class Incremental Learning (GCIL) by introducing the forgetting mechanism. We have found that integrating the forgetting mechanisms significantly enhances the models' performance in acquiring new knowledge.
  arXiv  Detail & Related papers  (2024-03-27T05:10:38Z)
• Improving In-Context Learning in Diffusion Models with Visual Context-Modulated Prompts [83.03471704115786]
  We introduce improved Prompt Diffusion (iPromptDiff) in this study. iPromptDiff integrates an end-to-end trained vision encoder that converts visual context into an embedding vector. We show that a diffusion-based vision foundation model, when equipped with this visual context-modulated text guidance and a standard ControlNet structure, exhibits versatility and robustness across a variety of training tasks.
  arXiv  Detail & Related papers  (2023-12-03T14:15:52Z)
• Rotation-equivariant Graph Neural Networks for Learning Glassy Liquids Representations [0.5249805590164901]
  We build a Graph Neural Network that learns a robust representation of the glass' static structure. We show that this constraint significantly improves the predictive power at comparable or reduced number of parameters. While remaining a Deep network, our model has improved interpretability compared to other GNNs.
  arXiv  Detail & Related papers  (2022-11-06T22:05:27Z)
• 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)
• The Neural Race Reduction: Dynamics of Abstraction in Gated Networks [12.130628846129973]
  We introduce the Gated Deep Linear Network framework that schematizes how pathways of information flow impact learning dynamics. We derive an exact reduction and, for certain cases, exact solutions to the dynamics of learning. Our work gives rise to general hypotheses relating neural architecture to learning and provides a mathematical approach towards understanding the design of more complex architectures.
  arXiv  Detail & Related papers  (2022-07-21T12:01:03Z)
• 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)
• Network representation learning systematic review: ancestors and current development state [1.0312968200748116]
  We present a systematic survey of network representation learning, known as network embedding, from birth to the current development state. We provide also formal definitions of basic concepts required to understand network representation learning. Most commonly used downstream tasks to evaluate embeddings, their evaluation metrics and popular datasets are highlighted.
  arXiv  Detail & Related papers  (2021-09-14T14:44:44Z)
• WeightScale: Interpreting Weight Change in Neural Networks [0.0]
  We present an approach to interpret learning in neural networks by measuring relative weight change on a per layer basis. We use this approach to investigate learning in the context of vision tasks across a variety of state-of-the-art networks.
  arXiv  Detail & Related papers  (2021-07-07T21:18:38Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)
• 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)
• Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond [114.39616146985001]
  In machine learning and computer vision fields, despite the different motivations and mechanisms, a lot of complex problems contain a series of closely related subproblms. In this paper, we first uniformly express these complex learning and vision problems from the perspective of Bi-Level Optimization (BLO) Then we construct a value-function-based single-level reformulation and establish a unified algorithmic framework to understand and formulate mainstream gradient-based BLO methodologies.
  arXiv  Detail & Related papers  (2021-01-27T16:20:23Z)
• Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
  We propose a topological perspective to represent a network into a complete graph for analysis. By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner. This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
  arXiv  Detail & Related papers  (2020-08-19T04:53:31Z)
• Concept Learners for Few-Shot Learning [76.08585517480807]
  We propose COMET, a meta-learning method that improves generalization ability by learning to learn along human-interpretable concept dimensions. We evaluate our model on few-shot tasks from diverse domains, including fine-grained image classification, document categorization and cell type annotation.
  arXiv  Detail & Related papers  (2020-07-14T22:04:17Z)

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.