轻量级图像分类模型通过内容自适应多轮处理提升效率
IMC-Net: A Lightweight Content-Conditioned Encoder with Multi-Pass Processing for Image Classification
- 用可复用的轻量核心块+评分选择器实现自适应深度计算
- 参数减少、推理更快，精度仍达主流水平
- 无需额外模块或微调，适配多种数据集
我们提出一种紧凑的图像分类编码器，通过内容感知的多轮处理实现计算经济性。模型仅使用一个轻量核心块，按需重复少量次数，由简单评分选择器决定特征图中每个区域是否需要进一步处理。该设计在不引入复杂辅助模块或专用预训练的前提下，实现输入相关的深度调节。在标准基准上，该方法以更少参数、更低浮点运算量和更快推理速度，达到与同类模型相当的精度。架构保持简洁，通过模块复用控制规模，并借助对选择得分的温和正则化确保训练稳定。我们讨论了高效掩码、轮次控制与表示缓存的实现策略，表明多轮策略可良好迁移至多个数据集，且无需任务定制。
原文摘要 · Abstract (English)
We present a compact encoder for image categorization that emphasizes computation economy through content-conditioned multi-pass processing. The model employs a single lightweight core block that can be re-applied a small number of times, while a simple score-based selector decides whether further passes are beneficial for each region unit in the feature map. This design provides input-conditioned depth without introducing heavy auxiliary modules or specialized pretraining. On standard benchmarks, the approach attains competitive accuracy with reduced parameters, lower floating-point operations, and faster inference compared to similarly sized baselines. The method keeps the architecture minimal, implements module reuse to control footprint, and preserves stable training via mild regularization on selection scores. We discuss implementation choices for efficient masking, pass control, and representation caching, and show that the multi-pass strategy transfers well to several datasets without requiring task-specific customization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。