arXiv cs.AI· Zeki Doruk Erden·· 10 天前AI 评分22
多尺度结构特征助力发展式学习框架实现持续且可理解的视觉识别
Multi-Scale Structural Features for Continual, Comprehensible Visual Recognition in a Developmental Learning Framework
AI 导读
研究者提出一种新的视觉特征表示，跨多个尺度编码形状结构，将边缘与轮廓特征及其空间关系结合，并融入网络精炼学习过程，同时改进学习动态与读出机制。在类增量 MNIST 基准上，该方法识别准确率大幅超过此前的特征表示，在存储量相当且不保存任何历史数据的情况下，匹配或超越基于回放与正则化的基线。其关键差异在于保持能力：基线会在同一周期内丢失刚训练的类别再重新学习，而该方法不会，且学到的表示保持人类可解释。
正文 · 原文
Abstract:Contemporary machine learning struggles to learn continually, reuse prior knowledge, and expose a comprehensible internal structure. A recently proposed developmental, gradient-free learning framework addresses these limitations by learning a discrete, topological model of its inputs through local variation and selection, yielding an inherent continual-learning guarantee: new observations refine existing structure without overwriting past knowledge, and without replay buffers or predefined task boundaries. Its extension to visual inputs demonstrated this principle on shape recognition, but relied on a feature representation of limited expressivity that capped recognition accuracy. We introduce a new visual feature representation that encodes shape structure across multiple scales, capturing edge and contour features together with their spatial relations, and integrate it with the network-refinement learning process; we further improve the learning dynamics and the read-out used to predict from the learned model. The study targets two-dimensional shape, with class-incremental MNIST as a controlled, interpretable benchmark in which continual-learning behavior can be measured directly. Our approach substantially increases accuracy over the prior representation, matching or exceeding replay- and regularisation-based baselines at comparable storage while storing no past data, and preserves the framework's defining behavior: earlier-learned classes are retained as new ones are introduced, with no destructive adaptation, and the learned representations remain human-interpretable. What separates the methods is retention: the baselines surrender most of a just-trained class within its own cycle and relearn it afterwards, which ours does not. The significance lies in the manner of learning. The system integrates information one sample at a time while provably preserving its responses to...
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2607.25531 [cs.LG] |
| (or arXiv:2607.25531v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2607.25531 arXiv-issued DOI via DataCite |
Submission history
From: Zeki Doruk Erden [view email]
[v1]
Tue, 28 Jul 2026 10:17:54 UTC (660 KB)
[v2]
Mon, 5 Oct 2026 19:20:39 UTC (911 KB)
来源：arXiv cs.AI · arxiv.org