Vision Hopfield Memory Networks

• URL: http://arxiv.org/abs/2603.25157v1
• Date: Thu, 26 Mar 2026 08:23:03 GMT
• Title: Vision Hopfield Memory Networks
• Abstract summary: Vision Hopfield Memory Network (V-HMN) is a brain-inspired foundation backbone that integrates hierarchical memory mechanisms with iterative refinement updates.<n>V-HMN captures both local and global dynamics in a unified framework.<n>Memory retrieval exposes the relationship between inputs and stored patterns, making decisions more interpretable.
• Score: 43.727500835033986
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent vision and multimodal foundation backbones, such as Transformer families and state-space models like Mamba, have achieved remarkable progress, enabling unified modeling across images, text, and beyond. Despite their empirical success, these architectures remain far from the computational principles of the human brain, often demanding enormous amounts of training data while offering limited interpretability. In this work, we propose the Vision Hopfield Memory Network (V-HMN), a brain-inspired foundation backbone that integrates hierarchical memory mechanisms with iterative refinement updates. Specifically, V-HMN incorporates local Hopfield modules that provide associative memory dynamics at the image patch level, global Hopfield modules that function as episodic memory for contextual modulation, and a predictive-coding-inspired refinement rule for iterative error correction. By organizing these memory-based modules hierarchically, V-HMN captures both local and global dynamics in a unified framework. Memory retrieval exposes the relationship between inputs and stored patterns, making decisions more interpretable, while the reuse of stored patterns improves data efficiency. This brain-inspired design therefore enhances interpretability and data efficiency beyond existing self-attention- or state-space-based approaches. We conducted extensive experiments on public computer vision benchmarks, and V-HMN achieved competitive results against widely adopted backbone architectures, while offering better interpretability, higher data efficiency, and stronger biological plausibility. These findings highlight the potential of V-HMN to serve as a next-generation vision foundation model, while also providing a generalizable blueprint for multimodal backbones in domains such as text and audio, thereby bridging brain-inspired computation with large-scale machine learning.

Related papers

• Memory for Large Language Models [18.001409529004807]
  We present a systematic, architecture-centric taxonomy of memory in large language models.<n>We formalize the granular mechanisms dictating memory writing, routing, state transitions, and consolidation.<n>This unified perspective elucidates the conceptual boundaries between computation-coupled and independently addressable memory.
  arXiv  Detail & Related papers  (2026-07-28T07:34:53Z)
• Toward a Multi-View Brain Network Foundation Model: Cross-View Consistency Learning Across Arbitrary Atlases [62.33465338932216]
  MV-BrainFM is a multi-view brain network foundation model designed to learn generalizable and scalable representations from brain networks constructed with arbitrary atlases.<n>Experiments on more than 20K subjects from 17 fMRI datasets show that MV-BrainFM consistently outperforms 14 existing brain network foundation models.
  arXiv  Detail & Related papers  (2026-03-20T11:55:00Z)
• MoVE: Mixture of Value Embeddings -- A New Axis for Scaling Parametric Memory in Autoregressive Models [0.9222161299777548]
  We introduce $textbfMoVE (Mixture of Value Embeddings)$, a mechanism that breaks the rigid structural coupling of model capacity to computational cost.<n>MoVE decouples memory from compute by introducing a global bank of learnable value embeddings shared across all attention layers.<n>We validate MoVE through strictly controlled experiments on two representative applications of autoregressive modeling: Text Generation and Image Generation.
  arXiv  Detail & Related papers  (2026-01-30T12:07:23Z)
• The AI Hippocampus: How Far are We From Human Memory? [77.04745635827278]
  Implicit memory refers to the knowledge embedded within the internal parameters of pre-trained transformers.<n>Explicit memory involves external storage and retrieval components designed to augment model outputs with dynamic, queryable knowledge representations.<n>Agentic memory introduces persistent, temporally extended memory structures within autonomous agents.
  arXiv  Detail & Related papers  (2026-01-14T03:24:08Z)
• A Neural Network Model of Complementary Learning Systems: Pattern Separation and Completion for Continual Learning [2.9123921488295768]
  Learning new information without forgetting prior knowledge is central to human intelligence.<n>In contrast, neural network models suffer from catastrophic forgetting when acquiring new information.<n>We develop a neurally plausible continual learning model that achieves close to state-of-the-art accuracy (90%)<n>Our work provides a functional template for modeling memory consolidation, generalization, and continual learning in both biological and artificial systems.
  arXiv  Detail & Related papers  (2025-07-15T15:05:26Z)
• Latent Structured Hopfield Network for Semantic Association and Retrieval [52.634915010996835]
  Episodic memory enables humans to recall past experiences by associating semantic elements such as objects, locations, and time into coherent event representations.<n>We propose the Latent Structured Hopfield Network (LSHN), a framework that integrates continuous Hopfield attractor dynamics into an autoencoder architecture.<n>Unlike traditional Hopfield networks, our model is trained end-to-end with gradient descent, achieving scalable and robust memory retrieval.
  arXiv  Detail & Related papers  (2025-06-02T04:24:36Z)
• Quantifying Memory Utilization with Effective State-Size [73.52115209375343]
  We develop a measure of textitmemory utilization'<n>This metric is tailored to the fundamental class of systems with textitinput-invariant and textitinput-varying linear operators
  arXiv  Detail & Related papers  (2025-04-28T08:12:30Z)
• Input-Driven Dynamics for Robust Memory Retrieval in Hopfield Networks [3.961279440272764]
  The Hopfield model provides a mathematically idealized yet insightful framework for understanding the mechanisms of memory storage and retrieval in the human brain. We propose a novel system framework in which the external input directly influences the neural synapses and shapes the energy landscape of the Hopfield model. This plasticity-based mechanism provides a clear energetic interpretation of the memory retrieval process and proves effective at correctly classifying highly mixed inputs.
  arXiv  Detail & Related papers  (2024-11-06T17:24:25Z)
• Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation [60.80423207808076]
  Capturing long-range dependencies while preserving high-resolution visual representations is crucial for dense prediction tasks such as human pose estimation.<n>We propose the Dynamic Visual State Space (DVSS) block, which augments visual state space models with multi-scale convolutional operations.<n>We build HRVMamba, a novel model for efficient high-resolution representation learning.
  arXiv  Detail & Related papers  (2024-10-04T06:19:29Z)
• Modern Hopfield Networks meet Encoded Neural Representations -- Addressing Practical Considerations [5.272882258282611]
  This paper introduces Hopfield HEN, a framework that integrates encoded representations into MHNs to improve pattern separability and reduce meta-stable states. We show that HEN can also be used for retrieval in the context of hetero association of images with natural language queries, thus removing the limitation of requiring access to partial content in the same domain.
  arXiv  Detail & Related papers  (2024-09-24T19:17:15Z)
• 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)

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.