Hippocampus-DETR: An Explicit Memory Object Detection Framework Based on Hippocampus Modeling

2026-06-26

AI Summary

This work addresses the absence of explicit memory mechanisms in existing object detection models, which limits their ability to store, retrieve, and complete visual features over the long term. To overcome this, the study introduces HipNet—a novel memory-augmented architecture inspired by the biological hippocampal system—and integrates it into the DETR framework. HipNet emulates key hippocampal subregions, including the entorhinal cortex, dentate gyrus, CA3, CA1, and subiculum, to enable pattern separation, memory completion, salience-based filtering, and information integration. Coupled with a hierarchical training strategy and attention mechanisms, the proposed method not only surpasses state-of-the-art detectors in accuracy but also demonstrates exceptional generalization and data efficiency across diverse tasks such as few-shot classification, multimodal feature construction, and image restoration.

Abstract

This paper addresses the lack of explicit memory mechanisms in current object detection models and proposes Hippocampus-DETR, a novel detection framework based on biological hippocampal memory modeling. This framework integrates a hippocampal memory network module, HipNet, into the DETR architecture and systematically simulates the anatomical structure and functional organization of hippocampal subregions, including the entorhinal cortex, dentate gyrus, CA3, CA1, and subiculum. Through this design, Hippocampus-DETR realizes pattern separation, pattern completion, importance filtering, and information integration of visual encoding features. During training, different memory submodules are optimized using a layer-wise training strategy, ultimately forming a memory system with memory retrieval and completion capabilities. Experimental results demonstrate that Hippocampus-DETR achieves higher detection accuracy than current mainstream models. More importantly, models equipped with this framework also exhibit excellent generalization ability and data efficiency in tasks such as few-shot image classification, multimodal feature construction, and image restoration. Subsequent experiments further validate the functional necessity and internal interpretability of each memory submodule. This study not only provides a novel object detection framework, but also offers a feasible technical pathway for integrating neurocognitive mechanisms with deep learning models, highlighting its significant value in improving model learning efficiency and task robustness. The project is available at https://github.com/2186cloud/hipnet.

Problem

• object detection
• explicit memory
• hippocampus modeling
• memory mechanism
• visual encoding

Innovation

• hippocampal modeling
• explicit memory mechanism
• object detection
• pattern separation and completion
• neuro-inspired deep learning