arXiv cs.AI· Khush Kataruka, Mohammad Muzammila, Zahid Akhtar, Raghavendra Ramachandra, Praveen Kumar Chandaliya·· 13 小时前AI 评分18
混合 CNN-Transformer 与知识自蒸馏提升香蕉品种分类的跨等级泛化能力
Enhancing Cross-Grade Generalization in Banana Variety Classification via Hybrid CNN-Transformers and Knowledge Self-Distillation
AI 导读
研究提出双流 Swin ResNet 混合框架，并用基于 KL 散度的自蒸馏对齐 CNN 与 Transformer 两路的概率特征表示，在 31,678 张香蕉图像（3 个品种、3 个质量等级）的 Leave-One-Grade-Out 评测下取得 81.25% 平均准确率，显著超过 CNN 与 Transformer 基线。
正文 · 原文
Abstract:In recent years, automated fruit classification systems have become a more critical component in precision agriculture for efficient yield estimation, quality control, and supply chain optimization. However, they still face significant challenges under varying quality, fruit maturity, illumination, texture degradation, morphological attributes, domain shift, and post-harvest handling conditions. In this study, we address the challenging issue of cross-grade banana variety classification. This is a real-world setting where models that have been trained on specific quality grades must generalize to unseen grades to handle significant domain shift. Under a rigorous Leave-One-Grade-Out evaluation protocol, we present a thorough comparative analysis of CNNs, ViTs, and dual-stream hybrid architectures using a large-scale dataset of 31,678 banana images with three varieties and three quality grades. Specifically, to address the drawbacks of single-paradigm frameworks, we present a dual-stream Swin ResNet hybrid framework enhanced with KL-divergence-based self-distillation to align probabilistic feature representations across the CNN and Transformer streams. Comprehensive experimental analyzes show that the presented hybrid framework with KL-divergence based self-distillation achieves better overall performance, i.e., it attains a mean accuracy of 81.25% and significantly surpasses CNN and Transformer baseline models. Qualitative analysis further confirms that the hybrid framework in this study improves discriminative feature transferability, improves attention localization, and stabilizes optimization.
| Comments: | 29 Pages, 9 Figures |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.29008 [cs.CV] |
| (or arXiv:2610.29008v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29008 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Praveen Chandaliya Dr [view email]
[v1]
Wed, 21 Oct 2026 00:19:09 UTC (4,980 KB)
来源：arXiv cs.AI · arxiv.org